相关论文: Analysis of Deep Clustering as Preprocessing for A…

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…

This paper introduces DNCASR, a novel end-to-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed transcription of long multi-party meetings. DNCASR uses two…

Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous…

This paper investigates the in-context learning abilities of the Whisper automatic speech recognition (ASR) models released by OpenAI. A novel speech-based in-context learning (SICL) approach is proposed for test-time adaptation, which can…

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…

We present a novel approach centered on the decoding stage of Automatic Speech Recognition (ASR) that enhances multilingual performance, especially for low-resource languages. It utilizes a cross-lingual embedding clustering method to…

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these…

We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate…

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this…

The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

This paper presents the system developed to address the MISP 2025 Challenge. For the diarization system, we proposed a hybrid approach combining a WavLM end-to-end segmentation method with a traditional multi-module clustering technique to…

This paper introduces a novel approach to speaker-attributed ASR transcription using a neural clustering method. With a parallel processing mechanism, diarisation and ASR can be applied simultaneously, helping to prevent the accumulation of…

Multi-talker overlapped speech poses a significant challenge for speech recognition and diarization. Recent research indicated that these two tasks are inter-dependent and complementary, motivating us to explore a unified modeling method to…

Code-switching automatic speech recognition (ASR) aims to transcribe speech that contains two or more languages accurately. To better capture language-specific speech representations and address language confusion in code-switching ASR, the…

Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single model. However, current state-of-the-art ASR models are typically evaluated on…

Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language model LLaDA for…