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

In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers with residual connections, followed by a stacked LSTM…

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to…

Voice activity detection (VAD) is an essential pre-processing step for tasks such as automatic speech recognition (ASR) and speaker recognition. A basic goal is to remove silent segments within an audio, while a more general VAD system…

Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization…

We present a system for keyword spotting that, except for a frontend component for feature generation, it is entirely contained in a deep neural network (DNN) model trained "end-to-end" to predict the presence of the keyword in a stream of…

Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR). AED models, however, still have drawbacks when deploying in commercial…

Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-based probabilistic…

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

Accurate transcription and speaker diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of…

Voice activity detection is the task of detecting speech regions in a given audio stream or recording. First, we design a neural network combining trainable filters and recurrent layers to tackle voice activity detection directly from the…

Speech foundation models have shown strong transferability across a wide range of speech applications. However, their robustness to age-related domain shift in speaker diarization remains underexplored. In this work, we present a…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Overlapped speech is notoriously problematic for speaker diarization systems. Consequently, the use of speech separation has recently been proposed to improve their performance. Although promising, speech separation models struggle with…

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Recently, a fully supervised speaker diarization approach was proposed (UIS-RNN) which models speakers using multiple instances of a parameter-sharing recurrent neural network. In this paper we propose qualitative modifications to the model…

This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…

In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query.However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations.…

Since diarization and source separation of meeting data are closely related tasks, we here propose an approach to perform the two objectives jointly. It builds upon the target-speaker voice activity detection (TS-VAD) diarization approach,…