相关论文: On permutation invariant training for speech sourc…

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due…

We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, applying BitFit on pre-trained BERT models is competitive with…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Achieving robust speech separation for overlapping speakers in various acoustic environments with noise and reverberation remains an open challenge. Although existing datasets are available to train separators for specific scenarios, they…

The recently-proposed mixture invariant training (MixIT) is an unsupervised method for training single-channel sound separation models in the sense that it does not require ground-truth isolated reference sources. In this paper, we…

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise,…

Sortformer is an encoder-based speaker diarization model designed for supervising speaker tagging in speech-to-text models. Instead of relying solely on permutation invariant loss (PIL), Sortformer introduces Sort Loss to resolve the…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are…

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture of two sources, with their…

End-to-end multi-talker speech recognition is an emerging research trend in the speech community due to its vast potential in applications such as conversation and meeting transcriptions. To the best of our knowledge, all existing research…

Speech separation has been extensively studied to deal with the cocktail party problem in recent years. All related approaches can be divided into two categories: time-frequency domain methods and time domain methods. In addition, some…

This paper proposes a new loss using short-time Fourier transform (STFT) spectra for the aim of training a high-performance neural speech waveform model that predicts raw continuous speech waveform samples directly. Not only amplitude…

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread…

While permutation invariant training (PIT) based continuous speech separation (CSS) significantly improves the conversation transcription accuracy, it often suffers from speech leakages and failures in separation at "hot spot" regions…

Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream tasks with different data modalities. A PFM (e.g., BERT, ChatGPT, and GPT-4) is trained on large-scale data which provides a reasonable parameter…

Short-time Fourier transform (STFT) is used as the front end of many popular successful monaural speech separation methods, such as deep clustering (DPCL), permutation invariant training (PIT) and their various variants. Since the frequency…

Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output projection. However, parameter sharing alone does not guarantee a stable token interface:…

For noisy environments, ensuring the robustness of keyword spotting (KWS) systems is essential. While much research has focused on noisy KWS, less attention has been paid to multi-talker mixed speech scenarios. Unlike the usual cocktail…

The source separation-based speech enhancement problem with multiple beamforming in reverberant indoor environments is addressed in this paper. We propose that more generic solutions should cope with time-varying dynamic scenarios with…