相关论文: Deferred NAM: Low-latency Top-K Context Injection …

Goal-oriented conversational interfaces are designed to accomplish specific tasks and typically have interactions that tend to span multiple turns adhering to a pre-defined structure and a goal. However, conventional neural language models…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work…

Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are…

End-to-End Automatic Speech Recognition (ASR) has advanced significantly yet still struggles with rare and domain-specific entities. This paper introduces a simple yet efficient prompt-based biasing technique for contextualized ASR,…

Semantic parsing (SP) is a core component of modern virtual assistants like Google Assistant and Amazon Alexa. While sequence-to-sequence-based auto-regressive (AR) approaches are common for conversational semantic parsing, recent studies…

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence. However, due to the lack of target dependency modelling in the decoder, the conditional generation process…

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…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We propose to use…

It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition (ASR) contextual biasing without introducing additional parameters. A common…

Context cues carry information which can improve multi-turn interactions in automatic speech recognition (ASR) systems. In this paper, we introduce a novel mechanism inspired by hyper-prompting to fuse textual context with acoustic…

Contextual biasing is essential to improving the recognition of rare and domain-specific words in an automatic speech recognition (ASR) system. While numerous methods have been proposed in recent years, most of them focus on offline…

The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods either sparsify the attention map with structured patterns or permanently evict tokens at…

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…