Related papers: ChunkFormer: Masked Chunking Conformer For Long-Fo…

Chord recognition serves as a critical task in music information retrieval due to the abstract and descriptive nature of chords in music analysis. While audio chord recognition systems have achieved significant accuracy for small…

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

The recently proposed Conformer architecture which combines convolution with attention to capture both local and global dependencies has become the \textit{de facto} backbone model for Automatic Speech Recognition~(ASR). Inherited from the…

The quadratic complexity of standard self-attention severely limits the application of Transformer-based models to long-context tasks. While efficient Transformer variants exist, they often require architectural changes and costly…

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies attempting to build integrated ASR models by connecting a…

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output sequences for CTC or RNN-T models. Unfortunately, the long…

Automatic speech recognition (ASR) models are normally trained to operate over single utterances, with a short duration of less than 30 seconds. This choice has been made in part due to computational constraints, but also reflects a common,…

Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture based on the standard Conformer…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy…

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and…

Recent advances in Audio-Visual Speech Recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed…

Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is…

Speech foundation models, such as OpenAI's Whisper, become the state of the art in speech understanding due to their strong accuracy and generalizability. Yet, their applications are mostly limited to processing pre-recorded speech, whereas…

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a…

This work presents \textsc{ChunkFT}, a memory-efficient fine-tuning framework that reformulates full-parameter fine-tuning around a dynamically activated working set. \textsc{ChunkFT} enables gradient computation for arbitrary sub-tensors…

Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transformers. Nevertheless, in general, the performance of these…