Jinglin Liu

Rongjie Huang, Mingze Li, Dongchao Yang et al.

Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spoken dialogue. With an increasing demand to evaluate multi-modal LLMs of human intention understanding and cooperation with foundation models, we outline the principles and processes and test AudioGPT in terms of consistency, capability, and robustness. Experimental results demonstrate the capabilities of AudioGPT in solving AI tasks with speech, music, sound, and talking head understanding and generation in multi-round dialogues, which empower humans to create rich and diverse audio content with unprecedented ease. Our system is publicly available at \url{https://github.com/AIGC-Audio/AudioGPT}.

Ziyue Jiang, Zhe Su, Zhou Zhao et al. · cmu

Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech (TTS) systems. However, previous approaches require substantial annotated training data and additional efforts from language experts, making it difficult to extend high-quality neural TTS systems to out-of-domain daily conversations and countless languages worldwide. This paper tackles the polyphone disambiguation problem from a concise and novel perspective: we propose Dict-TTS, a semantic-aware generative text-to-speech model with an online website dictionary (the existing prior information in the natural language). Specifically, we design a semantics-to-pronunciation attention (S2PA) module to match the semantic patterns between the input text sequence and the prior semantics in the dictionary and obtain the corresponding pronunciations; The S2PA module can be easily trained with the end-to-end TTS model without any annotated phoneme labels. Experimental results in three languages show that our model outperforms several strong baseline models in terms of pronunciation accuracy and improves the prosody modeling of TTS systems. Further extensive analyses demonstrate that each design in Dict-TTS is effective. The code is available at \url{https://github.com/Zain-Jiang/Dict-TTS}.

Ziyue Jiang, Yi Ren, Zhenhui Ye et al.

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. However, previous works usually encode speech into latent using audio codec and use autoregressive language models or diffusion models to generate it, which ignores the intrinsic nature of speech and may lead to inferior or uncontrollable results. We argue that speech can be decomposed into several attributes (e.g., content, timbre, prosody, and phase) and each of them should be modeled using a module with appropriate inductive biases. From this perspective, we carefully design a novel and large zero-shot TTS system called Mega-TTS, which is trained with large-scale wild data and models different attributes in different ways: 1) Instead of using latent encoded by audio codec as the intermediate feature, we still choose spectrogram as it separates the phase and other attributes very well. Phase can be appropriately constructed by the GAN-based vocoder and does not need to be modeled by the language model. 2) We model the timbre using global vectors since timbre is a global attribute that changes slowly over time. 3) We further use a VQGAN-based acoustic model to generate the spectrogram and a latent code language model to fit the distribution of prosody, since prosody changes quickly over time in a sentence, and language models can capture both local and long-range dependencies. We scale Mega-TTS to multi-domain datasets with 20K hours of speech and evaluate its performance on unseen speakers. Experimental results demonstrate that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS, speech editing, and cross-lingual TTS tasks, with superior naturalness, robustness, and speaker similarity due to the proper inductive bias of each module. Audio samples are available at https://mega-tts.github.io/demo-page.

Rongjie Huang, Jiawei Huang, Dongchao Yang et al.

Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. In this work, we propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps by 1) introducing pseudo prompt enhancement with a distill-then-reprogram approach, it alleviates data scarcity with orders of magnitude concept compositions by using language-free audios; 2) leveraging spectrogram autoencoder to predict the self-supervised audio representation instead of waveforms. Together with robust contrastive language-audio pretraining (CLAP) representations, Make-An-Audio achieves state-of-the-art results in both objective and subjective benchmark evaluation. Moreover, we present its controllability and generalization for X-to-Audio with "No Modality Left Behind", for the first time unlocking the ability to generate high-definition, high-fidelity audios given a user-defined modality input. Audio samples are available at https://Text-to-Audio.github.io

Rongjie Huang, Zhou Zhao, Huadai Liu et al.

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through the preliminary study on diffusion model parameterization, we find that previous gradient-based TTS models require hundreds or thousands of iterations to guarantee high sample quality, which poses a challenge for accelerating sampling. In this work, we propose ProDiff, on progressive fast diffusion model for high-quality text-to-speech. Unlike previous work estimating the gradient for data density, ProDiff parameterizes the denoising model by directly predicting clean data to avoid distinct quality degradation in accelerating sampling. To tackle the model convergence challenge with decreased diffusion iterations, ProDiff reduces the data variance in the target site via knowledge distillation. Specifically, the denoising model uses the generated mel-spectrogram from an N-step DDIM teacher as the training target and distills the behavior into a new model with N/2 steps. As such, it allows the TTS model to make sharp predictions and further reduces the sampling time by orders of magnitude. Our evaluation demonstrates that ProDiff needs only 2 iterations to synthesize high-fidelity mel-spectrograms, while it maintains sample quality and diversity competitive with state-of-the-art models using hundreds of steps. ProDiff enables a sampling speed of 24x faster than real-time on a single NVIDIA 2080Ti GPU, making diffusion models practically applicable to text-to-speech synthesis deployment for the first time. Our extensive ablation studies demonstrate that each design in ProDiff is effective, and we further show that ProDiff can be easily extended to the multi-speaker setting. Audio samples are available at \url{https://ProDiff.github.io/.}

Zhenhui Ye, Ziyue Jiang, Yi Ren et al.

Generating photo-realistic video portrait with arbitrary speech audio is a crucial problem in film-making and virtual reality. Recently, several works explore the usage of neural radiance field in this task to improve 3D realness and image fidelity. However, the generalizability of previous NeRF-based methods to out-of-domain audio is limited by the small scale of training data. In this work, we propose GeneFace, a generalized and high-fidelity NeRF-based talking face generation method, which can generate natural results corresponding to various out-of-domain audio. Specifically, we learn a variaitional motion generator on a large lip-reading corpus, and introduce a domain adaptative post-net to calibrate the result. Moreover, we learn a NeRF-based renderer conditioned on the predicted facial motion. A head-aware torso-NeRF is proposed to eliminate the head-torso separation problem. Extensive experiments show that our method achieves more generalized and high-fidelity talking face generation compared to previous methods.

Rongjie Huang, Jinglin Liu, Huadai Liu et al.

Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in speech representation learning. Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while still facing the following challenges: 1) Acoustic multimodality: the discrete units derived from speech with same content could be indeterministic due to the acoustic property (e.g., rhythm, pitch, and energy), which causes deterioration of translation accuracy; 2) high latency: current S2ST systems utilize autoregressive models which predict each unit conditioned on the sequence previously generated, failing to take full advantage of parallelism. In this work, we propose TranSpeech, a speech-to-speech translation model with bilateral perturbation. To alleviate the acoustic multimodal problem, we propose bilateral perturbation (BiP), which consists of the style normalization and information enhancement stages, to learn only the linguistic information from speech samples and generate more deterministic representations. With reduced multimodality, we step forward and become the first to establish a non-autoregressive S2ST technique, which repeatedly masks and predicts unit choices and produces high-accuracy results in just a few cycles. Experimental results on three language pairs demonstrate that BiP yields an improvement of 2.9 BLEU on average compared with a baseline textless S2ST model. Moreover, our parallel decoding shows a significant reduction of inference latency, enabling speedup up to 21.4x than autoregressive technique. Audio samples are available at \url{https://TranSpeech.github.io/}

Rongjie Huang, Yi Ren, Jinglin Liu et al.

Style transfer for out-of-domain (OOD) speech synthesis aims to generate speech samples with unseen style (e.g., speaker identity, emotion, and prosody) derived from an acoustic reference, while facing the following challenges: 1) The highly dynamic style features in expressive voice are difficult to model and transfer; and 2) the TTS models should be robust enough to handle diverse OOD conditions that differ from the source data. This paper proposes GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style transfer of OOD custom voice. GenerSpeech decomposes the speech variation into the style-agnostic and style-specific parts by introducing two components: 1) a multi-level style adaptor to efficiently model a large range of style conditions, including global speaker and emotion characteristics, and the local (utterance, phoneme, and word-level) fine-grained prosodic representations; and 2) a generalizable content adaptor with Mix-Style Layer Normalization to eliminate style information in the linguistic content representation and thus improve model generalization. Our evaluations on zero-shot style transfer demonstrate that GenerSpeech surpasses the state-of-the-art models in terms of audio quality and style similarity. The extension studies to adaptive style transfer further show that GenerSpeech performs robustly in the few-shot data setting. Audio samples are available at https://GenerSpeech.github.io/

Chenye Cui, Yi Ren, Jinglin Liu et al.

Video to sound generation aims to generate realistic and natural sound given a video input. However, previous video-to-sound generation methods can only generate a random or average timbre without any controls or specializations of the generated sound timbre, leading to the problem that people cannot obtain the desired timbre under these methods sometimes. In this paper, we pose the task of generating sound with a specific timbre given a video input and a reference audio sample. To solve this task, we disentangle each target sound audio into three components: temporal information, acoustic information, and background information. We first use three encoders to encode these components respectively: 1) a temporal encoder to encode temporal information, which is fed with video frames since the input video shares the same temporal information as the original audio; 2) an acoustic encoder to encode timbre information, which takes the original audio as input and discards its temporal information by a temporal-corrupting operation; and 3) a background encoder to encode the residual or background sound, which uses the background part of the original audio as input. To make the generated result achieve better quality and temporal alignment, we also adopt a mel discriminator and a temporal discriminator for the adversarial training. Our experimental results on the VAS dataset demonstrate that our method can generate high-quality audio samples with good synchronization with events in video and high timbre similarity with the reference audio.

Jiawei Huang, Chen Zhang, Yi Ren et al.

Voice conversion aims to modify the source speaker's voice to resemble the target speaker while preserving the original speech content. Despite notable advancements in voice conversion these days, multi-lingual voice conversion (including both monolingual and cross-lingual scenarios) has yet to be extensively studied. It faces two main challenges: 1) the considerable variability in prosody and articulation habits across languages; and 2) the rarity of paired multi-lingual datasets from the same speaker. In this paper, we propose MulliVC, a novel voice conversion system that only converts timbre and keeps original content and source language prosody without multi-lingual paired data. Specifically, each training step of MulliVC contains three substeps: In step one the model is trained with monolingual speech data; then, steps two and three take inspiration from back translation, construct a cyclical process to disentangle the timbre and other information (content, prosody, and other language-related information) in the absence of multi-lingual data from the same speaker. Both objective and subjective results indicate that MulliVC significantly surpasses other methods in both monolingual and cross-lingual contexts, demonstrating the system's efficacy and the viability of the three-step approach with cycle consistency. Audio samples can be found on our demo page (mullivc.github.io).

Qinglin Zhang, Chong Deng, Jiaqing Liu et al.

Listening to long video/audio recordings from video conferencing and online courses for acquiring information is extremely inefficient. Even after ASR systems transcribe recordings into long-form spoken language documents, reading ASR transcripts only partly speeds up seeking information. It has been observed that a range of NLP applications, such as keyphrase extraction, topic segmentation, and summarization, significantly improve users' efficiency in grasping important information. The meeting scenario is among the most valuable scenarios for deploying these spoken language processing (SLP) capabilities. However, the lack of large-scale public meeting datasets annotated for these SLP tasks severely hinders their advancement. To prompt SLP advancement, we establish a large-scale general Meeting Understanding and Generation Benchmark (MUG) to benchmark the performance of a wide range of SLP tasks, including topic segmentation, topic-level and session-level extractive summarization and topic title generation, keyphrase extraction, and action item detection. To facilitate the MUG benchmark, we construct and release a large-scale meeting dataset for comprehensive long-form SLP development, the AliMeeting4MUG Corpus, which consists of 654 recorded Mandarin meeting sessions with diverse topic coverage, with manual annotations for SLP tasks on manual transcripts of meeting recordings. To the best of our knowledge, the AliMeeting4MUG Corpus is so far the largest meeting corpus in scale and facilitates most SLP tasks. In this paper, we provide a detailed introduction of this corpus, SLP tasks and evaluation methods, baseline systems and their performance.

Zhenhui Ye, Ziyue Jiang, Yi Ren et al.

We are interested in a novel task, namely low-resource text-to-talking avatar. Given only a few-minute-long talking person video with the audio track as the training data and arbitrary texts as the driving input, we aim to synthesize high-quality talking portrait videos corresponding to the input text. This task has broad application prospects in the digital human industry but has not been technically achieved yet due to two challenges: (1) It is challenging to mimic the timbre from out-of-domain audio for a traditional multi-speaker Text-to-Speech system. (2) It is hard to render high-fidelity and lip-synchronized talking avatars with limited training data. In this paper, we introduce Adaptive Text-to-Talking Avatar (Ada-TTA), which (1) designs a generic zero-shot multi-speaker TTS model that well disentangles the text content, timbre, and prosody; and (2) embraces recent advances in neural rendering to achieve realistic audio-driven talking face video generation. With these designs, our method overcomes the aforementioned two challenges and achieves to generate identity-preserving speech and realistic talking person video. Experiments demonstrate that our method could synthesize realistic, identity-preserving, and audio-visual synchronized talking avatar videos.

Longbin Ji, Pengfei Wei, Yi Ren et al.

Co-speech gesture generation is crucial for automatic digital avatar animation. However, existing methods suffer from issues such as unstable training and temporal inconsistency, particularly in generating high-fidelity and comprehensive gestures. Additionally, these methods lack effective control over speaker identity and temporal editing of the generated gestures. Focusing on capturing temporal latent information and applying practical controlling, we propose a Controllable Co-speech Gesture Generation framework, named C2G2. Specifically, we propose a two-stage temporal dependency enhancement strategy motivated by latent diffusion models. We further introduce two key features to C2G2, namely a speaker-specific decoder to generate speaker-related real-length skeletons and a repainting strategy for flexible gesture generation/editing. Extensive experiments on benchmark gesture datasets verify the effectiveness of our proposed C2G2 compared with several state-of-the-art baselines. The link of the project demo page can be found at https://c2g2-gesture.github.io/c2_gesture

Qinglin Zhang, Chong Deng, Jiaqing Liu et al.

ICASSP2023 General Meeting Understanding and Generation Challenge (MUG) focuses on prompting a wide range of spoken language processing (SLP) research on meeting transcripts, as SLP applications are critical to improve users' efficiency in grasping important information in meetings. MUG includes five tracks, including topic segmentation, topic-level and session-level extractive summarization, topic title generation, keyphrase extraction, and action item detection. To facilitate MUG, we construct and release a large-scale meeting dataset, the AliMeeting4MUG Corpus.

Jinglin Liu, Chengxi Li, Yi Ren et al.

We are interested in a novel task, singing voice beautifying (SVB). Given the singing voice of an amateur singer, SVB aims to improve the intonation and vocal tone of the voice, while keeping the content and vocal timbre. Current automatic pitch correction techniques are immature, and most of them are restricted to intonation but ignore the overall aesthetic quality. Hence, we introduce Neural Singing Voice Beautifier (NSVB), the first generative model to solve the SVB task, which adopts a conditional variational autoencoder as the backbone and learns the latent representations of vocal tone. In NSVB, we propose a novel time-warping approach for pitch correction: Shape-Aware Dynamic Time Warping (SADTW), which ameliorates the robustness of existing time-warping approaches, to synchronize the amateur recording with the template pitch curve. Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one. To achieve this, we also propose a new dataset containing parallel singing recordings of both amateur and professional versions. Extensive experiments on both Chinese and English songs demonstrate the effectiveness of our methods in terms of both objective and subjective metrics. Audio samples are available at~\url{https://neuralsvb.github.io}. Codes: \url{https://github.com/MoonInTheRiver/NeuralSVB}.

Jinglin Liu, Chengxi Li, Yi Ren et al.

Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e.g., mel-spectrogram) given a music score. Previous singing acoustic models adopt a simple loss (e.g., L1 and L2) or generative adversarial network (GAN) to reconstruct the acoustic features, while they suffer from over-smoothing and unstable training issues respectively, which hinder the naturalness of synthesized singing. In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. DiffSinger is a parameterized Markov chain that iteratively converts the noise into mel-spectrogram conditioned on the music score. By implicitly optimizing variational bound, DiffSinger can be stably trained and generate realistic outputs. To further improve the voice quality and speed up inference, we introduce a shallow diffusion mechanism to make better use of the prior knowledge learned by the simple loss. Specifically, DiffSinger starts generation at a shallow step smaller than the total number of diffusion steps, according to the intersection of the diffusion trajectories of the ground-truth mel-spectrogram and the one predicted by a simple mel-spectrogram decoder. Besides, we propose boundary prediction methods to locate the intersection and determine the shallow step adaptively. The evaluations conducted on a Chinese singing dataset demonstrate that DiffSinger outperforms state-of-the-art SVS work. Extensional experiments also prove the generalization of our methods on text-to-speech task (DiffSpeech). Audio samples: https://diffsinger.github.io. Codes: https://github.com/MoonInTheRiver/DiffSinger. The old title of this work: "Diffsinger: Diffusion acoustic model for singing voice synthesis".

Zhenhui Ye, Tianyun Zhong, Yi Ren et al.

One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video. The existing methods fail to simultaneously achieve the goals of accurate 3D avatar reconstruction and stable talking face animation. Besides, while the existing works mainly focus on synthesizing the head part, it is also vital to generate natural torso and background segments to obtain a realistic talking portrait video. To address these limitations, we present Real3D-Potrait, a framework that (1) improves the one-shot 3D reconstruction power with a large image-to-plane model that distills 3D prior knowledge from a 3D face generative model; (2) facilitates accurate motion-conditioned animation with an efficient motion adapter; (3) synthesizes realistic video with natural torso movement and switchable background using a head-torso-background super-resolution model; and (4) supports one-shot audio-driven talking face generation with a generalizable audio-to-motion model. Extensive experiments show that Real3D-Portrait generalizes well to unseen identities and generates more realistic talking portrait videos compared to previous methods. Video samples and source code are available at https://real3dportrait.github.io .

Jiawei Huang, Yi Ren, Rongjie Huang et al.

Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data scarcity. Additionally, 2D spatial structures widely used in T2A works lead to unsatisfactory audio quality when generating variable-length audio samples since they do not adequately prioritize temporal information. To address these challenges, we propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio. Our approach includes several techniques to improve semantic alignment and temporal consistency: Firstly, we use pre-trained large language models (LLMs) to parse the text into structured <event & order> pairs for better temporal information capture. We also introduce another structured-text encoder to aid in learning semantic alignment during the diffusion denoising process. To improve the performance of variable length generation and enhance the temporal information extraction, we design a feed-forward Transformer-based diffusion denoiser. Finally, we use LLMs to augment and transform a large amount of audio-label data into audio-text datasets to alleviate the problem of scarcity of temporal data. Extensive experiments show that our method outperforms baseline models in both objective and subjective metrics, and achieves significant gains in temporal information understanding, semantic consistency, and sound quality.

Rongjie Huang, Huadai Liu, Xize Cheng et al.

Direct speech-to-speech translation (S2ST) aims to convert speech from one language into another, and has demonstrated significant progress to date. Despite the recent success, current S2ST models still suffer from distinct degradation in noisy environments and fail to translate visual speech (i.e., the movement of lips and teeth). In this work, we present AV-TranSpeech, the first audio-visual speech-to-speech (AV-S2ST) translation model without relying on intermediate text. AV-TranSpeech complements the audio stream with visual information to promote system robustness and opens up a host of practical applications: dictation or dubbing archival films. To mitigate the data scarcity with limited parallel AV-S2ST data, we 1) explore self-supervised pre-training with unlabeled audio-visual data to learn contextual representation, and 2) introduce cross-modal distillation with S2ST models trained on the audio-only corpus to further reduce the requirements of visual data. Experimental results on two language pairs demonstrate that AV-TranSpeech outperforms audio-only models under all settings regardless of the type of noise. With low-resource audio-visual data (10h, 30h), cross-modal distillation yields an improvement of 7.6 BLEU on average compared with baselines. Audio samples are available at https://AV-TranSpeech.github.io

Jinzheng He, Jinglin Liu, Zhenhui Ye et al.

We are interested in a challenging task, Realistic-Music-Score based Singing Voice Synthesis (RMS-SVS). RMS-SVS aims to generate high-quality singing voices given realistic music scores with different note types (grace, slur, rest, etc.). Though significant progress has been achieved, recent singing voice synthesis (SVS) methods are limited to fine-grained music scores, which require a complicated data collection pipeline with time-consuming manual annotation to align music notes with phonemes. Furthermore, these manual annotation destroys the regularity of note durations in music scores, making fine-grained music scores inconvenient for composing. To tackle these challenges, we propose RMSSinger, the first RMS-SVS method, which takes realistic music scores as input, eliminating most of the tedious manual annotation and avoiding the aforementioned inconvenience. Note that music scores are based on words rather than phonemes, in RMSSinger, we introduce word-level modeling to avoid the time-consuming phoneme duration annotation and the complicated phoneme-level mel-note alignment. Furthermore, we propose the first diffusion-based pitch modeling method, which ameliorates the naturalness of existing pitch-modeling methods. To achieve these, we collect a new dataset containing realistic music scores and singing voices according to these realistic music scores from professional singers. Extensive experiments on the dataset demonstrate the effectiveness of our methods. Audio samples are available at https://rmssinger.github.io/.

Ruiqi Li, Rongjie Huang, Lichao Zhang et al.

The speech-to-singing (STS) voice conversion task aims to generate singing samples corresponding to speech recordings while facing a major challenge: the alignment between the target (singing) pitch contour and the source (speech) content is difficult to learn in a text-free situation. This paper proposes AlignSTS, an STS model based on explicit cross-modal alignment, which views speech variance such as pitch and content as different modalities. Inspired by the mechanism of how humans will sing the lyrics to the melody, AlignSTS: 1) adopts a novel rhythm adaptor to predict the target rhythm representation to bridge the modality gap between content and pitch, where the rhythm representation is computed in a simple yet effective way and is quantized into a discrete space; and 2) uses the predicted rhythm representation to re-align the content based on cross-attention and conducts a cross-modal fusion for re-synthesize. Extensive experiments show that AlignSTS achieves superior performance in terms of both objective and subjective metrics. Audio samples are available at https://alignsts.github.io.

Zhenhui Ye, Jinzheng He, Ziyue Jiang et al.

Generating talking person portraits with arbitrary speech audio is a crucial problem in the field of digital human and metaverse. A modern talking face generation method is expected to achieve the goals of generalized audio-lip synchronization, good video quality, and high system efficiency. Recently, neural radiance field (NeRF) has become a popular rendering technique in this field since it could achieve high-fidelity and 3D-consistent talking face generation with a few-minute-long training video. However, there still exist several challenges for NeRF-based methods: 1) as for the lip synchronization, it is hard to generate a long facial motion sequence of high temporal consistency and audio-lip accuracy; 2) as for the video quality, due to the limited data used to train the renderer, it is vulnerable to out-of-domain input condition and produce bad rendering results occasionally; 3) as for the system efficiency, the slow training and inference speed of the vanilla NeRF severely obstruct its usage in real-world applications. In this paper, we propose GeneFace++ to handle these challenges by 1) utilizing the pitch contour as an auxiliary feature and introducing a temporal loss in the facial motion prediction process; 2) proposing a landmark locally linear embedding method to regulate the outliers in the predicted motion sequence to avoid robustness issues; 3) designing a computationally efficient NeRF-based motion-to-video renderer to achieves fast training and real-time inference. With these settings, GeneFace++ becomes the first NeRF-based method that achieves stable and real-time talking face generation with generalized audio-lip synchronization. Extensive experiments show that our method outperforms state-of-the-art baselines in terms of subjective and objective evaluation. Video samples are available at https://genefaceplusplus.github.io .

Shoutong Wang, Jinglin Liu, Yi Ren et al.

Multi-speaker singing voice synthesis is to generate the singing voice sung by different speakers. To generalize to new speakers, previous zero-shot singing adaptation methods obtain the timbre of the target speaker with a fixed-size embedding from single reference audio. However, they face several challenges: 1) the fixed-size speaker embedding is not powerful enough to capture full details of the target timbre; 2) single reference audio does not contain sufficient timbre information of the target speaker; 3) the pitch inconsistency between different speakers also leads to a degradation in the generated voice. In this paper, we propose a new model called MR-SVS to tackle these problems. Specifically, we employ both a multi-reference encoder and a fixed-size encoder to encode the timbre of the target speaker from multiple reference audios. The Multi-reference encoder can capture more details and variations of the target timbre. Besides, we propose a well-designed pitch shift method to address the pitch inconsistency problem. Experiments indicate that our method outperforms the baseline method both in naturalness and similarity.

Rongjie Huang, Feiyang Chen, Yi Ren et al.

High-fidelity multi-singer singing voice synthesis is challenging for neural vocoder due to the singing voice data shortage, limited singer generalization, and large computational cost. Existing open corpora could not meet requirements for high-fidelity singing voice synthesis because of the scale and quality weaknesses. Previous vocoders have difficulty in multi-singer modeling, and a distinct degradation emerges when conducting unseen singer singing voice generation. To accelerate singing voice researches in the community, we release a large-scale, multi-singer Chinese singing voice dataset OpenSinger. To tackle the difficulty in unseen singer modeling, we propose Multi-Singer, a fast multi-singer vocoder with generative adversarial networks. Specifically, 1) Multi-Singer uses a multi-band generator to speed up both training and inference procedure. 2) to capture and rebuild singer identity from the acoustic feature (i.e., mel-spectrogram), Multi-Singer adopts a singer conditional discriminator and conditional adversarial training objective. 3) to supervise the reconstruction of singer identity in the spectrum envelopes in frequency domain, we propose an auxiliary singer perceptual loss. The joint training approach effectively works in GANs for multi-singer voices modeling. Experimental results verify the effectiveness of OpenSinger and show that Multi-Singer improves unseen singer singing voices modeling in both speed and quality over previous methods. The further experiment proves that combined with FastSpeech 2 as the acoustic model, Multi-Singer achieves strong robustness in the multi-singer singing voice synthesis pipeline. Samples are available at https://Multi-Singer.github.io/

Aoxiong Yin, Zhou Zhao, Jinglin Liu et al.

Sign language translation as a kind of technology with profound social significance has attracted growing researchers' interest in recent years. However, the existing sign language translation methods need to read all the videos before starting the translation, which leads to a high inference latency and also limits their application in real-life scenarios. To solve this problem, we propose SimulSLT, the first end-to-end simultaneous sign language translation model, which can translate sign language videos into target text concurrently. SimulSLT is composed of a text decoder, a boundary predictor, and a masked encoder. We 1) use the wait-k strategy for simultaneous translation. 2) design a novel boundary predictor based on the integrate-and-fire module to output the gloss boundary, which is used to model the correspondence between the sign language video and the gloss. 3) propose an innovative re-encode method to help the model obtain more abundant contextual information, which allows the existing video features to interact fully. The experimental results conducted on the RWTH-PHOENIX-Weather 2014T dataset show that SimulSLT achieves BLEU scores that exceed the latest end-to-end non-simultaneous sign language translation model while maintaining low latency, which proves the effectiveness of our method.

Rongjie Huang, Chenye Cui, Feiyang Chen et al.

Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong expressiveness. Existing neural vocoders designed for text-to-speech cannot directly be applied to singing voice synthesis because they result in glitches and poor high-frequency reconstruction. In this work, we propose SingGAN, a generative adversarial network designed for high-fidelity singing voice synthesis. Specifically, 1) to alleviate the glitch problem in the generated samples, we propose source excitation with the adaptive feature learning filters to expand the receptive field patterns and stabilize long continuous signal generation; and 2) SingGAN introduces global and local discriminators at different scales to enrich low-frequency details and promote high-frequency reconstruction; and 3) To improve the training efficiency, SingGAN includes auxiliary spectrogram losses and sub-band feature matching penalty loss. To the best of our knowledge, SingGAN is the first work designed toward high-fidelity singing voice vocoding. Our evaluation of SingGAN demonstrates the state-of-the-art results with higher-quality (MOS 4.05) samples. Also, SingGAN enables a sample speed of 50x faster than real-time on a single NVIDIA 2080Ti GPU. We further show that SingGAN generalizes well to the mel-spectrogram inversion of unseen singers, and the end-to-end singing voice synthesis system SingGAN-SVS enjoys a two-stage pipeline to transform the music scores into expressive singing voices. Audio samples are available at \url{https://SingGAN.github.io/}

Yi Ren, Jinglin Liu, Zhou Zhao

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics features (e.g., prosody) even with small model size but suffers from blurry and unnatural results; and normalizing flow is good at reconstructing the frequency bin-wise details but performs poorly when the number of model parameters is limited. Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech model. Specifically, 1) to model both the prosody and mel-spectrogram details accurately, we adopt a lightweight VAE with an enhanced prior followed by a flow-based post-net with strong conditional inputs as the main architecture. 2) To further compress the model size and memory footprint, we introduce the grouped parameter sharing mechanism to the affine coupling layers in the post-net. 3) To improve the expressiveness of synthesized speech and reduce the dependency on accurate fine-grained alignment between text and speech, we propose a linguistic encoder with mixture alignment combining hard inter-word alignment and soft intra-word alignment, which explicitly extracts word-level semantic information. Experimental results show that PortaSpeech outperforms other TTS models in both voice quality and prosody modeling in terms of subjective and objective evaluation metrics, and shows only a slight performance degradation when reducing the model parameters to 6.7M (about 4x model size and 3x runtime memory compression ratio compared with FastSpeech 2). Our extensive ablation studies demonstrate that each design in PortaSpeech is effective.

Zhijie Lin, Zhou Zhao, Haoyuan Li et al.

Lip reading, aiming to recognize spoken sentences according to the given video of lip movements without relying on the audio stream, has attracted great interest due to its application in many scenarios. Although prior works that explore lip reading have obtained salient achievements, they are all trained in a non-simultaneous manner where the predictions are generated requiring access to the full video. To breakthrough this constraint, we study the task of simultaneous lip reading and devise SimulLR, a simultaneous lip Reading transducer with attention-guided adaptive memory from three aspects: (1) To address the challenge of monotonic alignments while considering the syntactic structure of the generated sentences under simultaneous setting, we build a transducer-based model and design several effective training strategies including CTC pre-training, model warm-up and curriculum learning to promote the training of the lip reading transducer. (2) To learn better spatio-temporal representations for simultaneous encoder, we construct a truncated 3D convolution and time-restricted self-attention layer to perform the frame-to-frame interaction within a video segment containing fixed number of frames. (3) The history information is always limited due to the storage in real-time scenarios, especially for massive video data. Therefore, we devise a novel attention-guided adaptive memory to organize semantic information of history segments and enhance the visual representations with acceptable computation-aware latency. The experiments show that the SimulLR achieves the translation speedup 9.10$\times$ compared with the state-of-the-art non-simultaneous methods, and also obtains competitive results, which indicates the effectiveness of our proposed methods.

Jinglin Liu, Zhiying Zhu, Yi Ren et al.

As a key component of talking face generation, lip movements generation determines the naturalness and coherence of the generated talking face video. Prior literature mainly focuses on speech-to-lip generation while there is a paucity in text-to-lip (T2L) generation. T2L is a challenging task and existing end-to-end works depend on the attention mechanism and autoregressive (AR) decoding manner. However, the AR decoding manner generates current lip frame conditioned on frames generated previously, which inherently hinders the inference speed, and also has a detrimental effect on the quality of generated lip frames due to error propagation. This encourages the research of parallel T2L generation. In this work, we propose a parallel decoding model for fast and high-fidelity text-to-lip generation (ParaLip). Specifically, we predict the duration of the encoded linguistic features and model the target lip frames conditioned on the encoded linguistic features with their duration in a non-autoregressive manner. Furthermore, we incorporate the structural similarity index loss and adversarial learning to improve perceptual quality of generated lip frames and alleviate the blurry prediction problem. Extensive experiments conducted on GRID and TCD-TIMIT datasets demonstrate the superiority of proposed methods. Video samples are available via \url{https://paralip.github.io/}.

Chenye Cui, Yi Ren, Jinglin Liu et al.

Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to generate a more emotional and more expressive speech is becoming a new challenge to researchers due to the scarcity of high-quality emotion speech dataset and the lack of advanced emotional TTS model. In this paper, we first briefly introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. After that, we propose a simple but efficient architecture for emotional speech synthesis called EMSpeech. Unlike those models which need additional reference audio as input, our model could predict emotion labels just from the input text and generate more expressive speech conditioned on the emotion embedding. In the experiment phase, we first validate the effectiveness of our dataset by an emotion classification task. Then we train our model on the proposed dataset and conduct a series of subjective evaluations. Finally, by showing a comparable performance in the emotional speech synthesis task, we successfully demonstrate the ability of the proposed model.

Chen Zhang, Yi Ren, Xu Tan et al.

While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available, which presents challenges for TTS model training for this speaker. Previous works usually address the challenge using two methods: 1) training the TTS model using the speech denoised with an enhancement model; 2) taking a single noise embedding as input when training with noisy speech. However, they usually cannot handle speech with real-world complicated noise such as those with high variations along time. In this paper, we develop DenoiSpeech, a TTS system that can synthesize clean speech for a speaker with noisy speech data. In DenoiSpeech, we handle real-world noisy speech by modeling the fine-grained frame-level noise with a noise condition module, which is jointly trained with the TTS model. Experimental results on real-world data show that DenoiSpeech outperforms the previous two methods by 0.31 and 0.66 MOS respectively.

Jinglin Liu, Yi Ren, Zhou Zhao et al.

Lipreading is an impressive technique and there has been a definite improvement of accuracy in recent years. However, existing methods for lipreading mainly build on autoregressive (AR) model, which generate target tokens one by one and suffer from high inference latency. To breakthrough this constraint, we propose FastLR, a non-autoregressive (NAR) lipreading model which generates all target tokens simultaneously. NAR lipreading is a challenging task that has many difficulties: 1) the discrepancy of sequence lengths between source and target makes it difficult to estimate the length of the output sequence; 2) the conditionally independent behavior of NAR generation lacks the correlation across time which leads to a poor approximation of target distribution; 3) the feature representation ability of encoder can be weak due to lack of effective alignment mechanism; and 4) the removal of AR language model exacerbates the inherent ambiguity problem of lipreading. Thus, in this paper, we introduce three methods to reduce the gap between FastLR and AR model: 1) to address challenges 1 and 2, we leverage integrate-and-fire (I\&F) module to model the correspondence between source video frames and output text sequence. 2) To tackle challenge 3, we add an auxiliary connectionist temporal classification (CTC) decoder to the top of the encoder and optimize it with extra CTC loss. We also add an auxiliary autoregressive decoder to help the feature extraction of encoder. 3) To overcome challenge 4, we propose a novel Noisy Parallel Decoding (NPD) for I\&F and bring Byte-Pair Encoding (BPE) into lipreading. Our experiments exhibit that FastLR achieves the speedup up to 10.97$\times$ comparing with state-of-the-art lipreading model with slight WER absolute increase of 1.5\% and 5.5\% on GRID and LRS2 lipreading datasets respectively, which demonstrates the effectiveness of our proposed method.

Jinglin Liu, Yi Ren, Xu Tan et al.

Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT). Since AT and NAT can share model structure and AT is an easier task than NAT due to the explicit dependency on previous target-side tokens, a natural idea is to gradually shift the model training from the easier AT task to the harder NAT task. To smooth the shift from AT training to NAT training, in this paper, we introduce semi-autoregressive translation (SAT) as intermediate tasks. SAT contains a hyperparameter k, and each k value defines a SAT task with different degrees of parallelism. Specially, SAT covers AT and NAT as its special cases: it reduces to AT when k = 1 and to NAT when k = N (N is the length of target sentence). We design curriculum schedules to gradually shift k from 1 to N, with different pacing functions and number of tasks trained at the same time. We called our method as task-level curriculum learning for NAT (TCL-NAT). Experiments on IWSLT14 De-En, IWSLT16 En-De, WMT14 En-De and De-En datasets show that TCL-NAT achieves significant accuracy improvements over previous NAT baselines and reduces the performance gap between NAT and AT models to 1-2 BLEU points, demonstrating the effectiveness of our proposed method.

Yi Ren, Jinglin Liu, Xu Tan et al.

Non-autoregressive (NAR) models generate all the tokens of a sequence in parallel, resulting in faster generation speed compared to their autoregressive (AR) counterparts but at the cost of lower accuracy. Different techniques including knowledge distillation and source-target alignment have been proposed to bridge the gap between AR and NAR models in various tasks such as neural machine translation (NMT), automatic speech recognition (ASR), and text to speech (TTS). With the help of those techniques, NAR models can catch up with the accuracy of AR models in some tasks but not in some others. In this work, we conduct a study to understand the difficulty of NAR sequence generation and try to answer: (1) Why NAR models can catch up with AR models in some tasks but not all? (2) Why techniques like knowledge distillation and source-target alignment can help NAR models. Since the main difference between AR and NAR models is that NAR models do not use dependency among target tokens while AR models do, intuitively the difficulty of NAR sequence generation heavily depends on the strongness of dependency among target tokens. To quantify such dependency, we propose an analysis model called CoMMA to characterize the difficulty of different NAR sequence generation tasks. We have several interesting findings: 1) Among the NMT, ASR and TTS tasks, ASR has the most target-token dependency while TTS has the least. 2) Knowledge distillation reduces the target-token dependency in target sequence and thus improves the accuracy of NAR models. 3) Source-target alignment constraint encourages dependency of a target token on source tokens and thus eases the training of NAR models.