Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization.

In this paper, we address the challenge of speech enhancement in real-world recordings, which often contain various forms of distortion, such as background noise, reverberation, and microphone artefacts. We revisit the use of Generative Adversarial Networks (GANs) for speech enhancement and theoretically show that GANs are naturally inclined to seek the point of maximum density within the conditional clean speech distribution, which, as we argue, is essential for the speech enhancement task. We study various feature extractors for perceptual loss to facilitate the stability of adversarial training, developing a methodology for probing the structure of the feature space. This leads us to integrate WavLM-based perceptual loss into MS-STFT adversarial training pipeline, creating an effective and stable training procedure for the speech enhancement model. The resulting speech enhancement model, which we refer to as FINALLY, builds upon the HiFi++ architecture, augmented with a WavLM encoder and a novel training pipeline. Empirical results on various datasets confirm our model's ability to produce clear, high-quality speech at 48 kHz, achieving state-of-the-art performance in the field of speech enhancement.

Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to yield separate models, leading to disjoint inference pipelines with increased memory requirements and redundancies. This paper proposes unified training strategies for these systems. We demonstrate that training a single model for all three tasks enhances VSR and AVSR performance, overcoming typical optimisation challenges when training from scratch. Moreover, we introduce a greedy pseudo-labelling approach to more effectively leverage unlabelled samples, addressing shortcomings in related self-supervised methods. Finally, we develop a self-supervised pretraining method within our framework, proving its effectiveness alongside our semi-supervised approach. Despite using a single model for all tasks, our unified approach achieves state-of-the-art performance compared to recent methods on LRS3 and LRS2 for ASR, VSR, and AVSR, as well as on the newly released WildVSR dataset. Code and models are available at https://github.com/

Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is represented by a segment of speech signal with variable length and unknown boundary, and this segmental structure makes learning the mapping between speech and text challenging, especially without paired data.

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based endto-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of the target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech.

Biological systems possess remarkable sound source localization (SSL) capabilities that are critical for survival in complex environments. This ability arises from the collaboration between the auditory periphery, which encodes sound as precisely timed spikes, and the auditory cortex, which performs spike-based computations. Inspired by these biological mechanisms, we propose a novel neuromorphic SSL framework that integrates spike-based neural encoding and computation. The framework employs Resonate-and-Fire (RF) neurons with a phase-locking coding (RF-PLC) method to achieve energy-efficient audio processing. The RF-PLC method leverages the resonance properties of RF neurons to efficiently convert audio signals to time-frequency representation and encode interaural time difference (ITD) cues into discriminative spike patterns.

Encouraged by the success of deep neural networks on a variety of visual tasks, much theoretical and experimental work has been aimed at understanding and interpreting how vision networks operate. Meanwhile, deep neural networks have also achieved impressive performance in audio processing applications, both as sub-components of larger systems and as complete end-to-end systems by themselves. Despite their empirical successes, comparatively little is understood about how these audio models accomplish these tasks. In this work, we employ a recently developed statistical mechanical theory that connects geometric properties of network representations and the separability of classes to probe how information is untangled within neural networks trained to recognize speech. We observe that speaker-specific nuisance variations are discarded by the network's hierarchy, whereas task-relevant properties such as words and phonemes are untangled in later layers. Higher level concepts such as parts-of-speech and context dependence also emerge in the later layers of the network. Finally, we find that the deep representations carry out significant temporal untangling by efficiently extracting task-relevant features at each time step of the computation. Taken together, these findings shed light on how deep auditory models process time dependent input signals to achieve invariant speech recognition, and show how different concepts emerge through the layers of the network.

Accurate emotion perception is crucial for various applications, including humancomputer interaction, education, and counseling. However, traditional singlemodality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal.

The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffuse noise, due to the lack of large-scale real-recorded datasets.

Speech serves as a ubiquitous input interface for embedded mobile devices. Cloud-based solutions, while offering powerful speech understanding services, raise significant concerns regarding user privacy. To address this, disentanglement-based encoders have been proposed to remove sensitive information from speech signals without compromising the speech understanding functionality. However, these encoders demand high memory usage and computation complexity, making them impractical for resource-constrained wimpy devices. Our solution is based on a key observation that speech understanding hinges on long-term dependency knowledge of the entire utterance, in contrast to privacysensitive elements that are short-term dependent. Exploiting this observation, we propose SILENCE, a lightweight system that selectively obscuring short-term details, without damaging the long-term dependent speech understanding performance. The crucial part of SILENCE is a differential mask generator derived from interpretable learning to automatically configure the masking process. We have implemented SILENCE on the STM32H7 microcontroller and evaluate its efficacy under different attacking scenarios. Our results demonstrate that SILENCE offers speech understanding performance and privacy protection capacity comparable to existing encoders, while achieving up to 53.3 speedup and 134.1 reduction in memory footprint.