Related papers: G-STAR: End-to-End Global Speaker-Tracking Attribu…
In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…
This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and…
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve…
When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…
We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was…
Clinical 12-lead ECG classification remains difficult because of diverse recording conditions, overlapping pathologies, and pronounced label imbalance hinder generalization, while unconstrained augmentations risk distorting diagnostically…
Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…
We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an integrated auxiliary block for text-based training. This…
In this paper, we propose a speaker verification method by an Attentive Multi-scale Convolutional Recurrent Network (AMCRN). The proposed AMCRN can acquire both local spatial information and global sequential information from the input…
In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking with incomplete modalities remains a challenging issue due…
Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an…
Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness…
Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels. Recent advances have shown that joint ASR and SD models can learn to…
End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we…
Most end-to-end (E2E) speech recognition models are composed of encoder and decoder blocks that perform acoustic and language modeling functions. Pretrained large language models (LLMs) have the potential to improve the performance of E2E…
End-to-end multi-talker automatic speech recognition (MTASR) faces significant challenges in accurately transcribing overlapping speech. A critical bottleneck is that speaker-specific acoustic characteristics, which are essential for…
Recent Automatic Speech Recognition systems have been moving towards end-to-end systems that can be trained together. Numerous techniques that have been proposed recently enabled this trend, including feature extraction with CNNs, context…
This paper proposes a novel online speaker diarization algorithm based on a fully supervised self-attention mechanism (SA-EEND). Online diarization inherently presents a speaker's permutation problem due to the possibility to assign speaker…
In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid…
Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit…