相关论文: Low-Latency Deep Clustering For Speech Separation

The performance of automatic speech recognition (ASR) systems severely degrades when multi-talker speech overlap occurs. In meeting environments, speech separation is typically performed to improve the robustness of ASR systems. Recently,…

In this paper two different approaches to enhance the performance of the most challenging component of a Speaker Diarization system are presented, i.e. the speaker clustering part. A processing step is proposed enhancing the input features…

This paper describes an effective unsupervised speaker indexing approach. We suggest a two stage algorithm to speed-up the state-of-the-art algorithm based on the Bayesian Information Criterion (BIC). In the first stage of the merging…

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker…

In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants. Applications include rejection of false wake-ups or unintended interactions as…

In this paper, we introduce a causal low-latency low-complexity approach for binaural multichannel blind speaker separation in noisy reverberant conditions. The model, referred to as Group Communication Binaural Filter and Sum Network…

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…

Significant performance degradation of automatic speech recognition (ASR) systems is observed when the audio signal contains cross-talk. One of the recently proposed approaches to solve the problem of multi-speaker ASR is the deep…

Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…

State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…

Nowadays, there is a strong need to deploy the target speaker separation (TSS) model on mobile devices with a limitation of the model size and computational complexity. To better perform TSS for mobile voice communication, we first make a…

Scaling test-time computation--generating and analyzing multiple or sequential outputs for a single input--has become a promising strategy for improving the reliability and quality of large language models (LLMs), as evidenced by advances…

Many speech enhancement (SE) methods rely on continuous representations. Recently, discrete audio tokens have been explored to enable autoregressive generation for SE. However, it remains unclear whether discretization itself consistently…

Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…

In this paper, we present an improved feedforward sequential memory networks (FSMN) architecture, namely Deep-FSMN (DFSMN), by introducing skip connections between memory blocks in adjacent layers. These skip connections enable the…

Audio source separation is usually achieved by estimating the short-time Fourier transform (STFT) magnitude of each source, and then applying a spectrogram inversion algorithm to retrieve time-domain signals. In particular, the multiple…

A robust multichannel speaker diarization and separation system is proposed by exploiting the spatio-temporal activity of the speakers. The system is realized in a hybrid architecture that combines the array signal processing units and the…

Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the standard time-and-frequency cross-domain representation for…

LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low. In this work, we present two techniques to further reduce it's complexity, aiming for a low-cost LPCNet…