相关论文: CALM: Joint Contextual Acoustic-Linguistic Modelin…

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…

Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an…

We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by…

New-age conversational agent systems perform both speech emotion recognition (SER) and automatic speech recognition (ASR) using two separate and often independent approaches for real-world application in noisy environments. In this paper,…

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…

Contextual biasing is an important and challenging task for end-to-end automatic speech recognition (ASR) systems, which aims to achieve better recognition performance by biasing the ASR system to particular context phrases such as person…

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns…

While speech large language models (SpeechLLMs) have advanced standard automatic speech recognition (ASR), contextual biasing for named entities and rare words remains challenging, especially at scale. To address this, we propose BR-ASR: a…

Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

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…

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

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…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this…

Recent work has shown that it is possible to train a single model to perform joint acoustic echo cancellation (AEC), speech enhancement, and voice separation, thereby serving as a unified frontend for robust automatic speech recognition…

Automatic Speech Recognition (ASR) systems have been evolving quickly and reaching human parity in certain cases. The systems usually perform pretty well on reading style and clean speech, however, most of the available systems suffer from…

We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech…

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and…