相关论文: Soundwave: Less is More for Speech-Text Alignment …

Conversational Spoken Language Models (SLMs) are emerging as a promising paradigm for real-time speech interaction. However, their capacity of temporal dynamics, including the ability to manage timing, tempo and simultaneous speaking,…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics…

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…

Large Audio-Language Models (LALMs) as judges have emerged as a prominent approach for evaluating speech generation quality, yet their ability to assess speaker consistency across multi-turn dialogues remains unexplored. We present…

The emergence of Large Language Models (LLMs) has shifted language model evaluation toward reasoning and problem-solving tasks as measures of general intelligence. Small Language Models (SLMs) -- defined here as models under 10B parameters…

Large Language Models (LLMs) are increasingly used in Spoken Language Understanding (SLU), where effective multimodal learning depends on the alignment between audio and text. Despite various fusion methods, no standard metric exists to…

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

Speech understanding is essential for interpreting the diverse forms of information embedded in spoken language, including linguistic, paralinguistic, and non-linguistic cues that are vital for effective human-computer interaction. The…

With the growing influence of Large Language Models (LLMs), there is increasing interest in integrating speech representations with them to enable more seamless multi-modal processing and speech understanding. This study introduces a novel…

There is a surge in interest in self-supervised learning approaches for end-to-end speech encoding in recent years as they have achieved great success. Especially, WavLM showed state-of-the-art performance on various speech processing…

Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where…

Slot filling is a crucial subtask in spoken language understanding (SLU), traditionally implemented as a cascade of speech recognition followed by one or more natural language understanding (NLU) components. The recent advent of…

Large language models (LLMs) have demonstrated strong instruction-following capabilities in text-based tasks. However, this ability often deteriorates in multimodal models after alignment with non-text modalities such as images or audio.…

Recent Large Audio-Language Models (LALMs) exhibit impressive capabilities in understanding audio content for conversational QA tasks. However, these models struggle to accurately understand timestamps for temporal localization (e.g.,…

Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in both temporal and emotional aspects while preserving the vocal timbre of a given brief reference audio. Existing methods focus primarily on reducing…

This paper proposes a novel user-defined keyword spotting framework that accurately detects audio keywords based on text enrollment. Since audio data possesses additional acoustic information compared to text, there are discrepancies…