Related papers: Punctuation Restoration in Spanish Customer Suppor…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Speech applications dealing with conversations require not only recognizing the spoken words but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems,…

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack methods are mostly investigated in voice assistant scenarios…

Interacting with a speech interface to query a Question Answering (QA) system is becoming increasingly popular. Typically, QA systems rely on passage retrieval to select candidate contexts and reading comprehension to extract the final…

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…

Presented here is a method for automatic punctuation restoration in Swedish using a BERT model. The method is based on KB-BERT, a publicly available, neural network language model pre-trained on a Swedish corpus by National Library of…

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…

Automatic Speech Recognition (ASR) is an imperfect process that results in certain mismatches in ASR output text when compared to plain written text or transcriptions. When plain text data is to be used to train systems for spoken language…

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming…

Speech Translation (ST) is the task of translating speech in one language into text in another language. Traditional cascaded approaches for ST, using Automatic Speech Recognition (ASR) and Machine Translation (MT) systems, are prone to…

Punctuation and Segmentation are key to readability in Automatic Speech Recognition (ASR), often evaluated using F1 scores that require high-quality human transcripts and do not reflect readability well. Human evaluation is expensive,…

Conventional automatic speech recognition systems do not produce punctuation marks which are important for the readability of the speech recognition results. They are also needed for subsequent natural language processing tasks such as…

Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. However, if the available unlabeled speech is mismatched to…

While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of languages and…

One solution to automatic speech recognition (ASR) of overlapping speakers is to separate speech and then perform ASR on the separated signals. Commonly, the separator produces artefacts which often degrade ASR performance. Addressing this…

This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…