Related papers: Full-Sum Decoding for Hybrid HMM based Speech Reco…

LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models. Incorporating them efficiently into decoding has been notoriously difficult. In…

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation,…

LSTM language models (LSTM-LMs) have been proven to be powerful and yielded significant performance improvements over count based n-gram LMs in modern speech recognition systems. Due to its infinite history states and computational load,…

We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but…

Recent developments in speech synthesis have produced systems capable of outcome intelligible speech, but now researchers strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple…

Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding…

While external language models (LMs) are often incorporated into the decoding stage of automated speech recognition systems, these models usually operate with limited context. Cross utterance information has been shown to be beneficial…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

This report describes a new technique for inducing the structure of Hidden Markov Models from data which is based on the general `model merging' strategy (Omohundro 1992). The process begins with a maximum likelihood HMM that directly…

The anti-interference capability of wireless links is a physical layer problem for edge computing. Although convolutional codes have inherent error correction potential due to the redundancy introduced in the data, the performance of the…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their highly varying statistics require tying or smoothing to…

Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for…

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep…

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We…

We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the…

In this work, we introduce a framework for speech summarization that leverages the processing and reasoning capabilities of large language models (LLMs). We propose an end-to-end system that combines an instruction-tuned LLM with an audio…

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…