相关论文: LS-EEND: Long-Form Streaming End-to-End Neural Dia…

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops…

Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…

Understanding how the brain responds to sensory inputs is challenging: brain recordings are partial, noisy, and high dimensional; they vary across sessions and subjects and they capture highly nonlinear dynamics. These challenges have led…

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…

We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy…

In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the…

This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level…

This paper presents a novel evaluation approach to text-based speaker diarization (SD), tackling the limitations of traditional metrics that do not account for any contextual information in text. Two new metrics are proposed, Text-based…

Target speaker extraction (TSE) aims to extract the target speaker's voice from the input mixture. Previous studies have concentrated on high-overlapping scenarios. However, real-world applications usually meet more complex scenarios like…

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown…

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

This paper presents a novel framework for joint speaker diarization (SD) and automatic speech recognition (ASR), named SLIDAR (sliding-window diarization-augmented recognition). SLIDAR can process arbitrary length inputs and can handle any…

We propose a novel neural network-based end-to-end acoustic echo cancellation (E2E-AEC) method capable of streaming inference, which operates effectively without reliance on traditional linear AEC (LAEC) techniques and time delay…

Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances,…

Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed…

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full…

Active speaker detection (ASD) is a multi-modal task that aims to identify who, if anyone, is speaking from a set of candidates. Current audio-visual approaches for ASD typically rely on visually pre-extracted face tracks (sequences of…