相关论文: End-to-End Speech Recognition and Disfluency Remov…

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…

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. If left unaddressed,…

Detecting disfluencies in spontaneous speech is an important preprocessing step in natural language processing and speech recognition applications. Existing works for disfluency detection have focused on designing a single objective only…

Automatic speech recognition (ASR) systems often falter while processing stuttering-related disfluencies -- such as involuntary blocks and word repetitions -- yielding inaccurate transcripts. A critical barrier to progress is the scarcity…

Recently, end-to-end ASR based either on sequence-to-sequence networks or on the CTC objective function gained a lot of interest from the community, achieving competitive results over traditional systems using robust but complex pipelines.…

Disfluency detection models now approach high accuracy on English text. However, little exploration has been done in improving the size and inference time of the model. At the same time, automatic speech recognition (ASR) models are moving…

Disfluencies commonly occur in conversational speech. Speech with disfluencies can result in noisy Automatic Speech Recognition (ASR) transcripts, which affects downstream tasks like machine translation. In this paper, we propose an…

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

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…

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…

End-to-End automatic speech recognition (ASR) models aim to learn a generalised speech representation to perform recognition. In this domain there is little research to analyse internal representation dependencies and their relationship to…

Automatic speech recognition (ASR) has been an essential component of computer assisted language learning (CALL) and computer assisted language testing (CALT) for many years. As this technology continues to develop rapidly, it is important…

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

Speech disfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no effective AI solution to systematically tackle this problem. We solidify the concept of disfluent speech and disfluent speech…

Speech-to-text translation pertains to the task of converting speech signals in a language to text in another language. It finds its application in various domains, such as hands-free communication, dictation, video lecture transcription,…

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…

Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR components in an end-to-end (E2E) fashion. This report…

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier…