Search

To advance continuous-valued token modeling and temporal-coherence enforcement, we propose FELLE, an autoregressive model that integrates language modeling with token-wise flow matching. By leveraging the autoregressive nature of language models and the generative efficacy of flow matching, FELLE effectively predicts continuous-valued tokens (mel-spectrograms). For each continuous-valued token, FELLE modifies the general prior distribution in flow matching by incorporating information from the previous step, improving coherence and stability. Furthermore, to enhance synthesis quality, FELLE introduces a coarse-to-fine flow-matching mechanism, generating continuous-valued tokens hierarchically, conditioned on the language model's output. Experimental results demonstrate the potential of incorporating flow-matching techniques in autoregressive mel-spectrogram modeling, leading to significant improvements in TTS generation quality, as shown in https://aka.ms/felle.

Recent advances in GPT-4o like multi-modality models have demonstrated remarkable progress for direct speech-to-speech conversation, with real-time speech interaction experience and strong speech understanding ability. However, current research focuses on discrete speech tokens to align with discrete text tokens for language modelling, which depends on an audio codec with residual connections or independent group tokens, such a codec usually leverages large scale and diverse datasets training to ensure that the discrete speech codes have good representation for varied domain, noise, style data reconstruction as well as a well-designed codec quantizer and encoder-decoder architecture for discrete token language modelling. This paper introduces Flow-Omni, a continuous speech token based GPT-4o like model, capable of real-time speech interaction and low streaming latency. Specifically, first, instead of cross-entropy loss only, we combine flow matching loss with a pretrained autoregressive LLM and a small MLP network to predict the probability distribution of the continuous-valued speech tokens from speech prompt. second, we incorporated the continuous speech tokens to Flow-Omni multi-modality training, thereby achieving robust speech-to-speech performance with discrete text tokens and continuous speech tokens together. Experiments demonstrate that, compared to discrete text and speech multi-modality training and its variants, the continuous speech tokens mitigate robustness issues by avoiding the inherent flaws of discrete speech code's representation loss for LLM.

Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet effective designs to better leverage richly described synthetic captions. Firstly, by observing a strong inverse effect in learning with synthetic captions -- the short synthetic captions can generally lead to MUCH higher performance than full-length ones -- we therefore fed only partial synthetic captions to the text encoder. Secondly, we incorporate an autoregressive captioner to mimic the recaptioning process -- by conditioning on the paired image input and web-crawled text description, the captioner learns to predict the full-length synthetic caption generated by advanced MLLMs. Experiments show that our framework significantly improves zero-shot performance in cross-modal retrieval tasks, setting new SOTA results on MSCOCO and Flickr30K. Moreover, such trained vision encoders can enhance the visual capability of LLaVA, showing strong improvements on a range of MLLM benchmarks. Our project page is https://ucsc-vlaa.github.io/CLIPS/., Comment: 12 pages

End-to-end speech translation (ST), which translates source language speech directly into target language text, has garnered significant attention in recent years. Many ST applications require strict length control to ensure that the translation duration matches the length of the source audio, including both speech and pause segments. Previous methods often controlled the number of words or characters generated by the Machine Translation model to approximate the source sentence's length without considering the isochrony of pauses and speech segments, as duration can vary between languages. To address this, we present improvements to the duration alignment component of our sequence-to-sequence ST model. Our method controls translation length by predicting the duration of speech and pauses in conjunction with the translation process. This is achieved by providing timing information to the decoder, ensuring it tracks the remaining duration for speech and pauses while generating the translation. The evaluation on the Zh-En test set of CoVoST 2, demonstrates that the proposed Isochrony-Controlled ST achieves 0.92 speech overlap and 8.9 BLEU, which has only a 1.4 BLEU drop compared to the ST baseline.

In this paper, we propose a fast extrinsic calibration method for fusing multiple inertial measurement units (MIMU) to improve visual-inertial odometry (VIO) localization accuracy. Currently, data fusion algorithms for MIMU highly depend on the number of inertial sensors. Based on the assumption that extrinsic parameters between inertial sensors are perfectly calibrated, the fusion algorithm provides better localization accuracy with more IMUs, while neglecting the effect of extrinsic calibration error. Our method builds two non-linear least-squares problems to estimate the MIMU relative position and orientation separately, independent of external sensors and inertial noises online estimation. Then we give the general form of the virtual IMU (VIMU) method and propose its propagation on manifold. We perform our method on datasets, our self-made sensor board, and board with different IMUs, validating the superiority of our method over competing methods concerning speed, accuracy, and robustness. In the simulation experiment, we show that only fusing two IMUs with our calibration method to predict motion can rival nine IMUs. Real-world experiments demonstrate better localization accuracy of the VIO integrated with our calibration method and VIMU propagation on manifold.

Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of the SLM. In this work, we examine codec tokens within SLM framework for speech generation to provide insights for effective codec design. We retrain existing high-performing neural codec models on the same data set and loss functions to compare their performance in a uniform setting. We integrate codec tokens into two SLM systems: masked-based parallel speech generation system and an auto-regressive (AR) plus non-auto-regressive (NAR) model-based system. Our findings indicate that better speech reconstruction in codec systems does not guarantee improved speech generation in SLM. A high-quality codec decoder is crucial for natural speech production in SLM, while speech intelligibility depends more on quantization mechanism., Comment: Accepted by SLT-2024

We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which are originally designed for audio compression and sacrifice fidelity compared to mel-spectrograms. Specifically, (i) instead of cross-entropy loss, we apply regression loss with a proposed spectrogram flux loss function to model the probability distribution of the continuous-valued tokens. (ii) we have incorporated variational inference into MELLE to facilitate sampling mechanisms, thereby enhancing the output diversity and model robustness. Experiments demonstrate that, compared to the two-stage codec language models VALL-E and its variants, the single-stage MELLE mitigates robustness issues by avoiding the inherent flaws of sampling discrete codes, achieves superior performance across multiple metrics, and, most importantly, offers a more streamlined paradigm. See https://aka.ms/melle for demos of our work.

This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despite its simplicity, E2 TTS achieves state-of-the-art zero-shot TTS capabilities that are comparable to or surpass previous works, including Voicebox and NaturalSpeech 3. The simplicity of E2 TTS also allows for flexibility in the input representation. We propose several variants of E2 TTS to improve usability during inference. See https://aka.ms/e2tts/ for demo samples., Comment: Accepted to SLT 2024. Added evaluation data, see https://github.com/microsoft/e2tts-test-suite for more details

With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strategies bring astonishing diversity to generation, but also pose robustness issues such as typos, omissions and repetition. In addition, the high sampling rate of audio also brings huge computational overhead to the inference process of autoregression. To address these issues, we propose VALL-E R, a robust and efficient zero-shot TTS system, building upon the foundation of VALL-E. Specifically, we introduce a phoneme monotonic alignment strategy to strengthen the connection between phonemes and acoustic sequence, ensuring a more precise alignment by constraining the acoustic tokens to match their associated phonemes. Furthermore, we employ a codec-merging approach to downsample the discrete codes in shallow quantization layer, thereby accelerating the decoding speed while preserving the high quality of speech output. Benefiting from these strategies, VALL-E R obtains controllablity over phonemes and demonstrates its strong robustness by approaching the WER of ground truth. In addition, it requires fewer autoregressive steps, with over 60% time reduction during inference. This research has the potential to be applied to meaningful projects, including the creation of speech for those affected by aphasia. Audio samples will be available at: https://aka.ms/valler., Comment: 15 pages, 5 figures

This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time. Based on its predecessor, VALL-E, the new iteration introduces two significant enhancements: Repetition Aware Sampling refines the original nucleus sampling process by accounting for token repetition in the decoding history. It not only stabilizes the decoding but also circumvents the infinite loop issue. Grouped Code Modeling organizes codec codes into groups to effectively shorten the sequence length, which not only boosts inference speed but also addresses the challenges of long sequence modeling. Our experiments on the LibriSpeech and VCTK datasets show that VALL-E 2 surpasses previous systems in speech robustness, naturalness, and speaker similarity. It is the first of its kind to reach human parity on these benchmarks. Moreover, VALL-E 2 consistently synthesizes high-quality speech, even for sentences that are traditionally challenging due to their complexity or repetitive phrases. The advantages of this work could contribute to valuable endeavors, such as generating speech for individuals with aphasia or people with amyotrophic lateral sclerosis. See https://aka.ms/valle2 for demos of VALL-E 2., Comment: Demo posted

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the speech reconstruction quality from discrete speech token is far from satisfaction depending on the compressed speech token compression ratio. Generative diffusion models trained with score-matching loss and continuous normalized flow trained with flow-matching loss have become prominent in generation of images as well as speech. LM based TTS systems usually quantize speech into discrete tokens and generate these tokens autoregressively, and finally use a diffusion model to up sample coarse-grained speech tokens into fine-grained codec features or mel-spectrograms before reconstructing into waveforms with vocoder, which has a high latency and is not realistic for real time speech applications. In this paper, we systematically investigate varied diffusion models for up sampling stage, which is the main bottleneck for streaming synthesis of LM and diffusion-based architecture, we present the model architecture, objective and subjective metrics to show quality and efficiency improvement.

Nano-engineering crystalline materials can be used to tailor their thermal properties. By adding new nanoscale phonon scattering centers and controlling their size, one can effectively decrease the phonon mean free path and hence the thermal conductivity of a fully crystalline material. In this letter, we use the 3$\omega$ method in the temperature range of 100-300 K to experimentally report on the more than threefold reduction of the thermal conductivity of an epitaxially-grown crystalline germanium thin film with embedded polydispersed crystalline \ch{Ge3Mn5} nano-inclusions with diameters ranging from 5 to 25~nm. A detailed analysis of the structure of the thin film coupled with Monte Carlo simulations of phonon transport highlight the role of the nano-inclusions volume fraction in the reduction of the phononic contribution to the thermal conductivity, in particular its temperature dependence, leading to a phonon mean free path that is set by geometrical constraints., Comment: Applied Physics Letters, In press

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose NaturalSpeech 3, a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt. With this factorization design, NaturalSpeech 3 can effectively and efficiently model intricate speech with disentangled subspaces in a divide-and-conquer way. Experiments show that NaturalSpeech 3 outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility, and achieves on-par quality with human recordings. Furthermore, we achieve better performance by scaling to 1B parameters and 200K hours of training data., Comment: Achieving human-level quality and naturalness on multi-speaker datasets (e.g., LibriSpeech) in a zero-shot way

Laughter is one of the most expressive and natural aspects of human speech, conveying emotions, social cues, and humor. However, most text-to-speech (TTS) systems lack the ability to produce realistic and appropriate laughter sounds, limiting their applications and user experience. While there have been prior works to generate natural laughter, they fell short in terms of controlling the timing and variety of the laughter to be generated. In this work, we propose ELaTE, a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt with precise control of laughter timing and expression. Specifically, ELaTE works on the audio prompt to mimic the voice characteristic, the text prompt to indicate the contents of the generated speech, and the input to control the laughter expression, which can be either the start and end times of laughter, or the additional audio prompt that contains laughter to be mimicked. We develop our model based on the foundation of conditional flow-matching-based zero-shot TTS, and fine-tune it with frame-level representation from a laughter detector as additional conditioning. With a simple scheme to mix small-scale laughter-conditioned data with large-scale pre-training data, we demonstrate that a pre-trained zero-shot TTS model can be readily fine-tuned to generate natural laughter with precise controllability, without losing any quality of the pre-trained zero-shot TTS model. Through objective and subjective evaluations, we show that ELaTE can generate laughing speech with significantly higher quality and controllability compared to conventional models. See https://aka.ms/elate/ for demo samples., Comment: See https://aka.ms/elate/ for demo samples, v2: subjective evaluation has been added

Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose "text shearing" to maintain the quality and availability of extended captions. In image-text retrieval, without introducing additional training cost, our method consistently obtains 5.6 ~ 35.0 and 16.8 ~ 46.1 improvement on Recall@1 under the fine-tuning and zero-shot settings, respectively. Notably, we obtain zero-shot results that are comparable to fine-tuning on target datasets, which encourages more exploration of the versatile use of MLLMs.

Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones. This is essential for addressing the challenges of data storage and training costs. Prevalent methods facilitate knowledge transfer by matching the gradients, embedding distributions, or training trajectories of synthetic images with those of the sampled original images. Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling. We argue that random sampling overlooks the evenness of the selected sample distribution, which may result in noisy or biased matching targets. Besides, the sample diversity is also not constrained by random sampling. Additionally, current methods predominantly focus on single-dimensional matching, where information is not fully utilized. To address these challenges, we propose a novel matching strategy called Dataset Distillation by Bidirectional REpresentAtive Matching (DREAM+), which selects representative original images for bidirectional matching. DREAM+ is applicable to a variety of mainstream dataset distillation frameworks and significantly reduces the number of distillation iterations by more than 15 times without affecting performance. Given sufficient training time, DREAM+ can further improve the performance and achieve state-of-the-art results. We have released the code at github.com/NUS-HPC-AI-Lab/DREAM+., Comment: This is an extension of the ICCV conference version

Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice variability, using text prompts (descriptions) is more user-friendly since speech prompts can be hard to find or may not exist at all. TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech. In this work, we introduce PromptTTS 2 to address these challenges with a variation network to provide variability information of voice not captured by text prompts, and a prompt generation pipeline to utilize the large language models (LLM) to compose high quality text prompts. Specifically, the variation network predicts the representation extracted from the reference speech (which contains full information about voice variability) based on the text prompt representation. For the prompt generation pipeline, it generates text prompts for speech with a speech language understanding model to recognize voice attributes (e.g., gender, speed) from speech and a large language model to formulate text prompts based on the recognition results. Experiments on a large-scale (44K hours) speech dataset demonstrate that compared to the previous works, PromptTTS 2 generates voices more consistent with text prompts and supports the sampling of diverse voice variability, thereby offering users more choices on voice generation. Additionally, the prompt generation pipeline produces high-quality text prompts, eliminating the large labeling cost. The demo page of PromptTTS 2 is available online., Comment: Demo page: https://speechresearch.github.io/prompttts2

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually quantize speech into discrete tokens and use language models to generate these tokens one by one, which suffer from unstable prosody, word skipping/repeating issue, and poor voice quality. In this paper, we develop NaturalSpeech 2, a TTS system that leverages a neural audio codec with residual vector quantizers to get the quantized latent vectors and uses a diffusion model to generate these latent vectors conditioned on text input. To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, robustness, and voice quality in a zero-shot setting, and performs novel zero-shot singing synthesis with only a speech prompt. Audio samples are available at https://speechresearch.github.io/naturalspeech2., Comment: A large-scale text-to-speech and singing voice synthesis system with latent diffusion models. Update: NaturalSpeech 2 extension to voice conversion and speech enhancement

We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the target language speech by using both the source language speech and the target language text as prompts. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. Experimental results show that it can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker's voice, emotion, and acoustic environment. Moreover, VALL-E X effectively alleviates the foreign accent problems, which can be controlled by a language ID. Audio samples are available at \url{https://aka.ms/vallex}., Comment: We encourage readers to listen to the audio samples on our demo page: \url{https://aka.ms/vallex}

Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate representations to bridge acoustic model and vocoder, which suffers from two limitations: 1) the continuous acoustic frames are hard to predict with phoneme only, and acoustic information like duration or pitch is also needed to solve the one-to-many problem, which is not easy to scale on large scale and noise datasets; 2) to achieve diverse speech output based on continuous speech features, complex VAE or flow-based models are usually required. In this paper, we propose FoundationTTS, a new speech synthesis system with a neural audio codec for discrete speech token extraction and waveform reconstruction and a large language model for discrete token generation from linguistic (phoneme) tokens. Specifically, 1) we propose a hierarchical codec network based on vector-quantized auto-encoders with adversarial training (VQ-GAN), which first extracts continuous frame-level speech representations with fine-grained codec, and extracts a discrete token from each continuous speech frame with coarse-grained codec; 2) we jointly optimize speech token, linguistic tokens, speaker token together with a large language model and predict the discrete speech tokens autoregressively. Experiments show that FoundationTTS achieves a MOS gain of +0.14 compared to the baseline system. In ASR customization tasks, our method achieves 7.09\% and 10.35\% WERR respectively over two strong customized ASR baselines.

Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art methods mainly constrain the sample synthesis process by matching synthetic images and the original ones regarding gradients, embedding distributions, or training trajectories. Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling. We argue that random sampling overlooks the evenness of the selected sample distribution, which may result in noisy or biased matching targets. Besides, the sample diversity is also not constrained by random sampling. These factors together lead to optimization instability in the distilling process and degrade the training efficiency. Accordingly, we propose a novel matching strategy named as \textbf{D}ataset distillation by \textbf{RE}present\textbf{A}tive \textbf{M}atching (DREAM), where only representative original images are selected for matching. DREAM is able to be easily plugged into popular dataset distillation frameworks and reduce the distilling iterations by more than 8 times without performance drop. Given sufficient training time, DREAM further provides significant improvements and achieves state-of-the-art performances., Comment: Efficient matching for dataset distillation

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable improvement in the biasing problem, there are still two drawbacks for further accuracy improvement. First, due to information limitation in text only hypothesis or weak performance of ASR model on rare domains, the CSC model may fail to correct phrases with similar pronunciation or anti-context cases where all biasing phrases are not present in the utterance. Second, there is a discrepancy between the training and inference of CSC. The bias list in training is randomly selected but in inference there may be more similarity between ground truth phrase and other phrases. To solve above limitations, in this paper we propose an improved non-autoregressive (NAR) spelling correction model for contextual biasing in E2E neural transducer-based ASR systems to improve the previous CSC model from two perspectives: Firstly, we incorporate acoustics information with an external attention as well as text hypotheses into CSC to better distinguish target phrase from dissimilar or irrelevant phrases. Secondly, we design a semantic aware data augmentation schema in training phrase to reduce the mismatch between training and inference to further boost the biasing accuracy. Experiments show that the improved method outperforms the baseline ASR+Biasing system by as much as 20.3% relative name recall gain and achieves stable improvement compared to the previous CSC method over different bias list name coverage ratio., Comment: Accepted by ICASSP 2023

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. See https://aka.ms/valle for demos of our work., Comment: Working in progress