Yang Zhang

Yang Zhang, Krishna C. Puvvada, Vitaly Lavrukhin et al.

We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR). The model consists of a TitaNet based speaker embedding module, a Conformer based masking as well as ASR modules. These modules are jointly optimized to transcribe a target-speaker, while ignoring speech from other speakers. For training we use Connectionist Temporal Classification (CTC) loss and introduce a scale-invariant spectrogram reconstruction loss to encourage the model better separate the target-speaker's spectrogram from mixture. We obtain state-of-the-art target-speaker word error rate (TS-WER) on WSJ0-2mix-extr (4.2%). Further, we report for the first time TS-WER on WSJ0-3mix-extr (12.4%), LibriSpeech2Mix (4.2%) and LibriSpeech3Mix (7.6%) datasets, establishing new benchmarks for TS-ASR. The proposed model will be open-sourced through NVIDIA NeMo toolkit.

Cheng-I Jeff Lai, Freda Shi, Puyuan Peng et al. · mit

We study phrase structure induction from visually-grounded speech. The core idea is to first segment the speech waveform into sequences of word segments, and subsequently induce phrase structure using the inferred segment-level continuous representations. We present the Audio-Visual Neural Syntax Learner (AV-NSL) that learns phrase structure by listening to audio and looking at images, without ever being exposed to text. By training on paired images and spoken captions, AV-NSL exhibits the capability to infer meaningful phrase structures that are comparable to those derived by naturally-supervised text parsers, for both English and German. Our findings extend prior work in unsupervised language acquisition from speech and grounded grammar induction, and present one approach to bridge the gap between the two topics.

Hansong Zhang, Jiangjian Guo, Kun Li et al.

Offline handwritten signature verification systems are used to verify the identity of individuals, through recognizing their handwritten signature image as genuine signatures or forgeries. The main tasks of signature verification systems include extracting features from signature images and training a classifier for classification. The challenges of these tasks are twofold. First, genuine signatures and skilled forgeries are highly similar in their appearances, resulting in a small inter-class distance. Second, the instances of skilled forgeries are often unavailable, when signature verification models are being trained. To tackle these problems, this paper proposes a new signature verification method. It is the first model that employs a variational autoencoder (VAE) to extract features directly from signature images. To make the features more discriminative, it improves the traditional VAEs by introducing a new loss function for feature disentangling. In addition, it relies on SVM (Support Vector Machine) for classification according to the extracted features. Extensive experiments are conducted on two public datasets: MCYT-75 and GPDS-synthetic where the proposed method significantly outperformed $13$ representative offline signature verification methods. The achieved improvement in distinctive datasets indicates the robustness and great potential of the developed system in real application.

Peihao Chen, Yang Zhang, Mingkui Tan et al.

We focus on the task of generating sound from natural videos, and the sound should be both temporally and content-wise aligned with visual signals. This task is extremely challenging because some sounds generated \emph{outside} a camera can not be inferred from video content. The model may be forced to learn an incorrect mapping between visual content and these irrelevant sounds. To address this challenge, we propose a framework named REGNET. In this framework, we first extract appearance and motion features from video frames to better distinguish the object that emits sound from complex background information. We then introduce an innovative audio forwarding regularizer that directly considers the real sound as input and outputs bottlenecked sound features. Using both visual and bottlenecked sound features for sound prediction during training provides stronger supervision for the sound prediction. The audio forwarding regularizer can control the irrelevant sound component and thus prevent the model from learning an incorrect mapping between video frames and sound emitted by the object that is out of the screen. During testing, the audio forwarding regularizer is removed to ensure that REGNET can produce purely aligned sound only from visual features. Extensive evaluations based on Amazon Mechanical Turk demonstrate that our method significantly improves both temporal and content-wise alignment. Remarkably, our generated sound can fool the human with a 68.12% success rate. Code and pre-trained models are publicly available at https://github.com/PeihaoChen/regnet

Zijian Lin, Yang Zhang, Yougen Yuan et al.

Modern autoregressive speech synthesis models leveraging language models have demonstrated remarkable performance. However, the sequential nature of next token prediction in these models leads to significant latency, hindering their deployment in scenarios where inference speed is critical. In this work, we propose Speech Speculative Decoding (SSD), a novel framework for autoregressive speech synthesis acceleration. Specifically, our method employs a lightweight draft model to generate candidate token sequences, which are subsequently verified in parallel by the target model using the proposed SSD framework. Experimental results demonstrate that SSD achieves a significant speedup of 1.4x compared with conventional autoregressive decoding, while maintaining high fidelity and naturalness. Subjective evaluations further validate the effectiveness of SSD in preserving the perceptual quality of the target model while accelerating inference.

Tianyi Xie, Liucheng Liao, Cheng Bi et al.

The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video. Albeit moderate improvements in current approaches, they commonly require high-quality homologous data sources of videos and audios, thus causing the failure to leverage heterogeneous data sufficiently. In practice, it may be intractable to collect the perfect homologous data in some cases, for example, audio-corrupted or picture-blurry videos. To explore this kind of data and support high-fidelity few-shot visual dubbing, in this paper, we novelly propose a simple yet efficient two-stage framework with a higher flexibility of mining heterogeneous data. Specifically, our two-stage paradigm employs facial landmarks as intermediate prior of latent representations and disentangles the lip movements prediction from the core task of realistic talking head generation. By this means, our method makes it possible to independently utilize the training corpus for two-stage sub-networks using more available heterogeneous data easily acquired. Besides, thanks to the disentanglement, our framework allows a further fine-tuning for a given talking head, thereby leading to better speaker-identity preserving in the final synthesized results. Moreover, the proposed method can also transfer appearance features from others to the target speaker. Extensive experimental results demonstrate the superiority of our proposed method in generating highly realistic videos synchronized with the speech over the state-of-the-art.

Mark R. Saddler, Andrew Francl, Jenelle Feather et al.

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of using deep feature representations as 'perceptual' losses with which to train denoising systems. We explored their utility by first training deep neural networks to classify either spoken words or environmental sounds from audio. We then trained an audio transform to map noisy speech to an audio waveform that minimized the difference in the deep feature representations between the output audio and the corresponding clean audio. The resulting transforms removed noise substantially better than baseline methods trained to reconstruct clean waveforms, and also outperformed previous methods using deep feature losses. However, a similar benefit was obtained simply by using losses derived from the filter bank inputs to the deep networks. The results show that deep features can guide speech enhancement, but suggest that they do not yet outperform simple alternatives that do not involve learned features.

Yu Gu, Xiang Yin, Yonghui Rao et al.

This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders. Different from the conventional SVS models, the proposed ByteSing employs Tacotron-like encoder-decoder structures as the acoustic models, in which the CBHG models and recurrent neural networks (RNNs) are explored as encoders and decoders respectively. Meanwhile an auxiliary phoneme duration prediction model is utilized to expand the input sequence, which can enhance the model controllable capacity, model stability and tempo prediction accuracy. WaveRNN neural vocoders are also adopted as neural vocoders to further improve the voice quality of synthesized songs. Both objective and subjective experimental results prove that the SVS method proposed in this paper can produce quite natural, expressive and high-fidelity songs by improving the pitch and spectrogram prediction accuracy and the models using attention mechanism can achieve best performance.

Kaizhi Qian, Yang Zhang, Shiyu Chang et al.

Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would otherwise be too complicated. On the other hand, deep learning based enhancement approaches are able to learn complicated speech distributions and perform efficient inference, but they are unable to deal with variable number of input channels. Also, deep learning approaches introduce a lot of errors, particularly in the presence of unseen noise types and settings. We have therefore proposed an enhancement framework called DEEPBEAM, which combines the two complementary classes of algorithms. DEEPBEAM introduces a beamforming filter to produce natural sounding speech, but the filter coefficients are determined with the help of a monaural speech enhancement neural network. Experiments on synthetic and real-world data show that DEEPBEAM is able to produce clean, dry and natural sounding speech, and is robust against unseen noise.