Related papers: CIF-based Collaborative Decoding for End-to-end Co…

Children's speech recognition remains challenging due to substantial acoustic and linguistic variability, limited labeled data, and significant differences from adult speech. Speech foundation models can address these challenges through…

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

As large language models continue to develop and expand, the extensive public data they rely on faces the risk of depletion. Consequently, leveraging private data within organizations to enhance the performance of large models has emerged…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Passage reranking is a critical task in various applications, particularly when dealing with large volumes of documents. Existing neural architectures have limitations in retrieving the most relevant passage for a given question because the…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

Human-computer interaction (HCI) is significantly impacted by delayed responses from a spoken dialogue system. Hence, end-to-end (e2e) spoken language understanding (SLU) solutions have recently been proposed to decrease latency. Such…

We study speech intent classification and slot filling (SICSF) by proposing to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model, which achieves the new state-of-the-art…

Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems…

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

We propose the In-context Autoencoder (ICAE), leveraging the power of a large language model (LLM) to compress a long context into short compact memory slots that can be directly conditioned on by the LLM for various purposes. ICAE is first…

The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist…

Bias in predictive machine learning (ML) models is a fundamental challenge due to the skewed or unfair outcomes produced by biased models. Existing mitigation strategies rely on either post-hoc corrections or rigid constraints. However,…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Recently, to mitigate the confusion between different languages in code-switching (CS) automatic speech recognition (ASR), the conditionally factorized models, such as the language-aware encoder (LAE), explicitly disregard the contextual…

End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance drops substantially.…

Automatic speech recognition (ASR) systems typically rely on an external endpointer (EP) model to identify speech boundaries. In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask…

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a CTC-based end-to-end…

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…