Related papers: Unlocking Speech Instruction Data Potential with Q…

Existing Speech Language Model (SLM) scaling analysis paints a bleak picture. It predicts that SLMs require much more compute and data compared to text, leading some to question the feasibility of training high-quality SLMs. However, modern…

The success of large language models (LLMs) has prompted efforts to integrate speech and audio data, aiming to create general foundation models capable of processing both textual and non-textual inputs. Recent advances, such as GPT-4o,…

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

Conversational query rewriting is crucial for effective conversational search, yet traditional supervised methods require substantial labeled data, which is scarce in low-resource settings. This paper introduces Prompt-Guided In-Context…

Recent advances in large language model (LLM) training have highlighted the need for diverse, high-quality instruction data. Recently, many works are exploring synthetic data generation using LLMs. However, they primarily focus on prompt…

This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…

High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language understanding (NLU). Previous works on constructing NLU…

Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is…

Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have further expanded this capability to perceive multimodal audio…

Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. However,…

Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech. However, an LLM-based strategy for modeling spoken dialogs remains elusive, calling for further…

Time series data is fundamental to decision-making across many domains including healthcare, finance, power systems, and logistics. However, analyzing this data correctly often requires incorporating unstructured contextual information,…

Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit and culturally variable. We propose a human-large language model (LLM) collaborative…

Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic data is not always advantageous for improving training…

The previous state-of-the-art (SOTA) method achieved a remarkable execution accuracy on the Spider dataset, which is one of the largest and most diverse datasets in the Text-to-SQL domain. However, during our reproduction of the business…

Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle…

The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…

Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, a comparison of various generation strategies for low-resource language settings is lacking. While…

Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many…

Large Language Models (LLMs) have been applied in the speech domain, often incurring a performance drop due to misaligned between speech and language representations. To bridge this gap, we propose a joint speech and language model (SLM)…