相关论文: BLSTM-Based Confidence Estimation for End-to-End S…

While end-to-end (E2E) automatic speech recognition (ASR) models excel at general transcription, they struggle to recognize rare or unseen named entities (e.g., contact names, locations), which are critical for downstream applications like…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search,…

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

Automatic Short Answer Grading (ASAG) with generative large language models (LLMs) has recently demonstrated strong performance without task-specific fine-tuning, while also enabling the generation of synthetic feedback for educational…

We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition (ASR): hybrid Deep Bidirectional LSTM - Hidden Markov Models…

Current progress in artificial intelligence is centered around so-called large language models that consist of neural networks processing long sequences of high-dimensional vectors called tokens. Statistical physics provides powerful tools…

Even with several advancements in multilingual modeling, it is challenging to recognize multiple languages using a single neural model, without knowing the input language and most multilingual models assume the availability of the input…

Despite advances in Automatic Speech Recognition (ASR), transcription errors persist and require manual correction. Confidence scores, which indicate the certainty of ASR results, could assist users in identifying and correcting errors.…

The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text…

Transformer-based models have recently made significant achievements in the application of end-to-end (E2E) automatic speech recognition (ASR). It is possible to deploy the E2E ASR system on smart devices with the help of Transformer-based…

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

Non-intrusive speech intelligibility prediction remains challenging due to variability in speakers, noise conditions, and subjective perception. We propose an uncertainty-aware approach that leverages Whisper embeddings in combination with…

Recent developments using End-to-End Deep Learning models have been shown to have near or better performance than state of the art Recurrent Neural Networks (RNNs) on Automatic Speech Recognition tasks. These models tend to be lighter…

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on…

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

Neural sequence-to-sequence automatic speech recognition (ASR) systems are in principle open vocabulary systems, when using appropriate modeling units. In practice, however, they often fail to recognize words not seen during training, e.g.,…

Modern Automatic Speech Recognition (ASR) systems primarily rely on scores from an Acoustic Model (AM) and a Language Model (LM) to rescore the N-best lists. With the abundance of recent natural language processing advances, the information…

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more…