Related papers: Internal Language Model Adaptation with Text-Only …

Current speech LLMs bridge speech foundation models to LLMs using projection layers, training all of these components on speech instruction data. This strategy is computationally intensive and susceptible to task and prompt overfitting. We…

Sparse autoencoders (SAEs) are a popular method for decomposing Large Langage Models (LLM) activations into interpretable latents. However, due to their substantial training cost, most academic research uses open-source SAEs which are only…

Adapting pre-trained language models (PLMs) for time-series text classification amidst evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance detection. This study benchmarks the effectiveness of…

Decoder-only LLMs have shown impressive performance in MT due to their ability to learn from extensive datasets and generate high-quality translations. However, LLMs often struggle with the nuances and style required for…

Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a…

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parameters than a conventional ASR system, thus making it suitable…

Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Both text-to-image generation and large language models (LLMs) have made significant advancements. However, many text-to-image models still employ the somewhat outdated T5 and CLIP as their text encoders. In this work, we investigate the…

Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains remains…

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work…

State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncertainty and lead to over-fitting and poor generalization when…

The integration of speech into Large Language Models (LLMs) has substantially expanded their capabilities, but often at the cost of weakening their core textual competence. This degradation limits the ability of speech-enabled LLMs to fully…

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…

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints.…

End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deployment across domains (e.g., cities). Although several works…

Spoken language models (SLMs) that integrate speech with large language models (LMs) rely on modality adapters (MAs) to map the output of speech encoders to a representation that is understandable to the decoder LM. Yet we know very little…

Automatic speech recognition (ASR) systems normally consist of an acoustic model (AM) and a language model (LM). The acoustic model estimates the probability distribution of text given the input speech, while the language model calibrates…

Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and document summarization. This paper addresses the challenges of achieving high long-context…