Related papers: Promising Accurate Prefix Boosting for sequence-to…

Consistency regularization has recently been applied to semi-supervised sequence-to-sequence (S2S) automatic speech recognition (ASR). This principle encourages an ASR model to output similar predictions for the same input speech with…

Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction. Current prediction techniques for PSTs rely on exact matching between the suffix of the current sequence and the previously observed sequence. We…

In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the…

The theory of boosting provides a computational framework for aggregating approximate weak learning algorithms, which perform marginally better than a random predictor, into an accurate strong learner. In the realizable case, the success of…

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…

There are two major approaches for sequence labeling. One is the probabilistic gradient-based methods such as conditional random fields (CRF) and neural networks (e.g., RNN), which have high accuracy but drawbacks: slow training, and no…

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…

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the…

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

Joint punctuated and normalized automatic speech recognition (ASR) aims at outputing transcripts with and without punctuation and casing. This task remains challenging due to the lack of paired speech and punctuated text data in most ASR…

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other…

This paper presents a self-supervised learning method for pointer-generator networks to improve spoken-text normalization. Spoken-text normalization that converts spoken-style text into style normalized text is becoming an important…

Speech recognition, especially name recognition, is widely used in phone services such as company directory dialers, stock quote providers or location finders. It is usually challenging due to pronunciation variations. This paper proposes…

This paper explores speculative speech recognition (SSR), where we empower conventional automatic speech recognition (ASR) with speculation capabilities, allowing the recognizer to run ahead of audio. We introduce a metric for measuring SSR…

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

In this paper, we introduce an enhanced textual adversarial attack method, known as Saliency Attention and Semantic Similarity driven adversarial Perturbation (SASSP). The proposed scheme is designed to improve the effectiveness of…

We present paired learning and inference algorithms for significantly reducing computation and increasing speed of the vector dot products in the classifiers that are at the heart of many NLP components. This is accomplished by partitioning…

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Open-vocabulary keyword spotting (OV-KWS) enables personalized device control via arbitrary voice commands. Recently, researchers have explored using audio-text joint embeddings, allowing users to enroll phrases with text, and proposed…

Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by…