Related papers: Smart Speech Segmentation using Acousto-Linguistic…
In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…
Automatic Speech Recognition (ASR) systems generalize poorly on accented speech. The phonetic and linguistic variability of accents present hard challenges for ASR systems today in both data collection and modeling strategies. The resulting…
Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…
Typical ASR systems segment the input audio into utterances using purely acoustic information, which may not resemble the sentence-like units that are expected by conventional machine translation (MT) systems for Spoken Language…
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…
The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often…
While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers.…
A challenge in spoken language translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we fine-tune a general-purpose, large language model…
Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for…
Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…
Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task. It was shown that single-channel frame-level diarization with serialized output training…
With the growing adoption of wearable devices such as smart glasses for AI assistants, wearer speech recognition (WSR) is becoming increasingly critical to next-generation human-computer interfaces. However, in real environments,…
We propose a method of segmenting long-form speech by separating semantically complete sentences within the utterance. This prevents the ASR decoder from needlessly processing faraway context while also preventing it from missing relevant…
Modern smart glasses leverage advanced audio sensing and machine learning technologies to offer real-time transcribing and captioning services, considerably enriching human experiences in daily communications. However, such systems…
Speech translation (ST) automatically converts utterances in a source language into text in another language. Splitting continuous speech into shorter segments, known as speech segmentation, plays an important role in ST. Recent…
Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…
Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded…
Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual…
Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…