相关论文: Whisper-CD: Accurate Long-Form Speech Recognition …

Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Domain-specific speech remains a persistent challenge for automatic speech recognition (ASR), even for state-of-the-art systems like OpenAI's Whisper. We introduce Whisper: Courtside Edition, a novel multi-agent large language model (LLM)…

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…

We propose a speaker-attributed (SA) Whisper-based model for multi-talker speech recognition that combines target-speaker modeling with serialized output training (SOT). Our approach leverages a Diarization-Conditioned Whisper (DiCoW)…

Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. However, despite this growing use, current LVLMs often confuse or mismatch visual information originating from…

In this work, we investigate the time series representation learning problem using self-supervised techniques. Contrastive learning is well-known in this area as it is a powerful method for extracting information from the series and…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

Fault-tolerant quantum computers use decoders to monitor for errors and find a plausible correction. A decoder may provide a decoder confidence score (DCS) to gauge its success. We adopt a swim distance DCS, computed from the shortest path…

Large Vision-Language Models (LVLMs) demonstrate significant progress in multimodal understanding and reasoning, yet object hallucination remains a critical challenge. While existing research focuses on mitigating language priors or…

We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks: audio-visual speech recognition (AVSR), code-switched speech…

Multilingual speech emotion recognition aims to estimate a speaker's emotional state using a contactless method across different languages. However, variability in voice characteristics and linguistic diversity poses significant challenges…

Large-scale in-the-wild speech datasets have become more prevalent in recent years due to increased interest in models that can learn useful features from unlabelled data for tasks such as speech recognition or synthesis. These datasets…

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series,…

OpenAI's Whisper has achieved significant success in Automatic Speech Recognition. However, it has consistently been found to exhibit hallucination issues, particularly in non-speech segments, which limits its broader application in complex…

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of…

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech…

We propose a novel approach to end-to-end automatic speech recognition (ASR) to achieve efficient speech in-context learning (SICL) for (i) long-form speech decoding, (ii) test-time speaker adaptation, and (iii) test-time contextual…

Recent research on word-level confidence estimation for speech recognition systems has primarily focused on lightweight models known as Confidence Estimation Modules (CEMs), which rely on hand-engineered features derived from Automatic…