Related papers: Improved Robustness to Disfluencies in RNN-Transdu…

Compared to hybrid automatic speech recognition (ASR) systems that use a modular architecture in which each component can be independently adapted to a new domain, recent end-to-end (E2E) ASR system are harder to customize due to their…

Detecting and segmenting dysfluencies is crucial for effective speech therapy and real-time feedback. However, most methods only classify dysfluencies at the utterance level. We introduce StutterCut, a semi-supervised framework that…

Stuttering is a varied speech disorder that harms an individual's communication ability. Persons who stutter (PWS) often use speech therapy to cope with their condition. Improving speech recognition systems for people with such non-typical…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Stuttering is a speech disorder where the natural flow of speech is interrupted by blocks, repetitions or prolongations of syllables, words and phrases. The majority of existing automatic speech recognition (ASR) interfaces perform poorly…

Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer…

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have…

For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition…

When translating from speech, special consideration for conversational speech phenomena such as disfluencies is necessary. Most machine translation training data consists of well-formed written texts, causing issues when translating…

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…

Addressing the detrimental impact of non-stationary environmental noise on automatic speech recognition (ASR) has been a persistent and significant research focus. Despite advancements, this challenge continues to be a major concern.…

Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational…

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have…

Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often take advantage of statistical language archetypes captured…

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal…

Spoken Language Understanding (SLU) systems parse speech into semantic structures like dialog acts and slots. This involves the use of an Automatic Speech Recognizer (ASR) to transcribe speech into multiple text alternatives (hypotheses).…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

In recent years, the natural language processing community has moved away from task-specific feature engineering, i.e., researchers discovering ad-hoc feature representations for various tasks, in favor of general-purpose methods that learn…

Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains challenging, as existing…