Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and memory. Recent models incorporate new layers and modules along with transformers for better performance but also introduce extra model complexity. In this work, we replace transformers with Mamba, a selective state space model, for speech separation. We propose dual-path Mamba, which models short-term and long-term forward and backward dependency of speech signals using selective state spaces. Our experimental results on the WSJ0-2mix data show that our dual-path Mamba models match or outperform dual-path transformer models Sepformer with only 60% of its parameters, and the QDPN with only 30% of its parameters. Our large model also reaches a new state-of-the-art SI-SNRi of 24.4 dB.
In daily life, we encounter a variety of sounds, both desirable and undesirable, with limited control over their presence and volume. Our work introduces "Listen, Chat, and Edit" (LCE), a novel multimodal sound mixture editor that modifies each sound source in a mixture based on user-provided text instructions. LCE distinguishes itself with a user-friendly chat interface and its unique ability to edit multiple sound sources simultaneously within a mixture, without needing to separate them. Users input open-vocabulary text prompts, which are interpreted by a large language model to create a semantic filter for editing the sound mixture. The system then decomposes the mixture into its components, applies the semantic filter, and reassembles it into the desired output. We developed a 160-hour dataset with over 100k mixtures, including speech and various audio sources, along with text prompts for diverse editing tasks like extraction, removal, and volume control. Our experiments demonstrate significant improvements in signal quality across all editing tasks and robust performance in zero-shot scenarios with varying numbers and types of sound sources.
Recent advancements in artificial intelligence have sparked interest in the parallels between large language models (LLMs) and human neural processing, particularly in language comprehension. While prior research has established similarities in the representation of LLMs and the brain, the underlying computational principles that cause this convergence, especially in the context of evolving LLMs, remain elusive. Here, we examined a diverse selection of high-performance LLMs with similar parameter sizes to investigate the factors contributing to their alignment with the brain's language processing mechanisms. We find that as LLMs achieve higher performance on benchmark tasks, they not only become more brain-like as measured by higher performance when predicting neural responses from LLM embeddings, but also their hierarchical feature extraction pathways map more closely onto the brain's while using fewer layers to do the same encoding. We also compare the feature extraction pathways of the LLMs to each other and identify new ways in which high-performing models have converged toward similar hierarchical processing mechanisms. Finally, we show the importance of contextual information in improving model performance and brain similarity. Our findings reveal the converging aspects of language processing in the brain and LLMs and offer new directions for developing models that align more closely with human cognitive processing.
In this study, we present a simple multi-channel framework for contrastive learning (MC-SimCLR) to encode 'what' and 'where' of spatial audios. MC-SimCLR learns joint spectral and spatial representations from unlabeled spatial audios, thereby enhancing both event classification and sound localization in downstream tasks. At its core, we propose a multi-level data augmentation pipeline that augments different levels of audio features, including waveforms, Mel spectrograms, and generalized cross-correlation (GCC) features. In addition, we introduce simple yet effective channel-wise augmentation methods to randomly swap the order of the microphones and mask Mel and GCC channels. By using these augmentations, we find that linear layers on top of the learned representation significantly outperform supervised models in terms of both event classification accuracy and localization error. We also perform a comprehensive analysis of the effect of each augmentation method and a comparison of the fine-tuning performance using different amounts of labeled data.
Recent advancements in speech synthesis have leveraged GAN-based networks like HiFi-GAN and BigVGAN to produce high-fidelity waveforms from mel-spectrograms. However, these networks are computationally expensive and parameter-heavy. iSTFTNet addresses these limitations by integrating inverse short-time Fourier transform (iSTFT) into the network, achieving both speed and parameter efficiency. In this paper, we introduce an extension to iSTFTNet, termed HiFTNet, which incorporates a harmonic-plus-noise source filter in the time-frequency domain that uses a sinusoidal source from the fundamental frequency (F0) inferred via a pre-trained F0 estimation network for fast inference speed. Subjective evaluations on LJSpeech show that our model significantly outperforms both iSTFTNet and HiFi-GAN, achieving ground-truth-level performance. HiFTNet also outperforms BigVGAN-base on LibriTTS for unseen speakers and achieves comparable performance to BigVGAN while being four times faster with only $1/6$ of the parameters. Our work sets a new benchmark for efficient, high-quality neural vocoding, paving the way for real-time applications that demand high quality speech synthesis.
In recent years, large-scale pre-trained speech language models (SLMs) have demonstrated remarkable advancements in various generative speech modeling applications, such as text-to-speech synthesis, voice conversion, and speech enhancement. These applications typically involve mapping text or speech inputs to pre-trained SLM representations, from which target speech is decoded. This paper introduces a new approach, SLMGAN, to leverage SLM representations for discriminative tasks within the generative adversarial network (GAN) framework, specifically for voice conversion. Building upon StarGANv2-VC, we add our novel SLM-based WavLM discriminators on top of the mel-based discriminators along with our newly designed SLM feature matching loss function, resulting in an unsupervised zero-shot voice conversion system that does not require text labels during training. Subjective evaluation results show that SLMGAN outperforms existing state-of-the-art zero-shot voice conversion models in terms of naturalness and achieves comparable similarity, highlighting the potential of SLM-based discriminators for related applications.
In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with our novel differentiable duration modeling for end-to-end training, resulting in improved speech naturalness. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. Moreover, when trained on the LibriTTS dataset, our model outperforms previous publicly available models for zero-shot speaker adaptation. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs. The audio demos and source code are available at https://styletts2.github.io/.
Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of previously learned tasks, which undermines the model's ability to perform well over the long term. This paper introduces a new approach to continual audio representation learning called DeCoR. Unlike other methods that store previous data, features, or models, DeCoR indirectly distills knowledge from an earlier model to the latest by predicting quantization indices from a delayed codebook. We demonstrate that DeCoR improves acoustic scene classification accuracy and integrates well with continual self-supervised representation learning. Our approach introduces minimal storage and computation overhead, making it a lightweight and efficient solution for continual learning.
Binaural speech separation in real-world scenarios often involves moving speakers. Most current speech separation methods use utterance-level permutation invariant training (u-PIT) for training. In inference time, however, the order of outputs can be inconsistent over time particularly in long-form speech separation. This situation which is referred to as the speaker swap problem is even more problematic when speakers constantly move in space and therefore poses a challenge for consistent placement of speakers in output channels. Here, we describe a real-time binaural speech separation model based on a Wavesplit network to mitigate the speaker swap problem for moving speaker separation. Our model computes a speaker embedding for each speaker at each time frame from the mixed audio, aggregates embeddings using online clustering, and uses cluster centroids as speaker profiles to track each speaker throughout the long duration. Experimental results on reverberant, long-form moving multitalker speech separation show that the proposed method is less prone to speaker swap and achieves comparable performance with u-PIT based models with ground truth tracking in both separation accuracy and preserving the interaural cues.
Auditory attention decoding (AAD) is a technique used to identify and amplify the talker that a listener is focused on in a noisy environment. This is done by comparing the listener's brainwaves to a representation of all the sound sources to find the closest match. The representation is typically the waveform or spectrogram of the sounds. The effectiveness of these representations for AAD is uncertain. In this study, we examined the use of self-supervised learned speech representation in improving the accuracy and speed of AAD. We recorded the brain activity of three subjects using invasive electrocorticography (ECoG) as they listened to two conversations and focused on one. We used WavLM to extract a latent representation of each talker and trained a spatiotemporal filter to map brain activity to intermediate representations of speech. During the evaluation, the reconstructed representation is compared to each speaker's representation to determine the target speaker. Our results indicate that speech representation from WavLM provides better decoding accuracy and speed than the speech envelope and spectrogram. Our findings demonstrate the advantages of self-supervised learned speech representation for auditory attention decoding and pave the way for developing brain-controlled hearable technologies.