Related papers: ConPCO: Preserving Phoneme Characteristics for Aut…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been…

Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio input. We analyze these grounding failures and identify a…

RLVR has become a widely adopted paradigm for improving LLMs' reasoning capabilities, and GRPO is one of its most representative algorithms. In this paper, we first show that GRPO admits an equivalent discriminative reformulation as a…

The Vocal Joystick Vowel Corpus, by Washington University, was used to study monophthongs pronounced by native English speakers. The objective of this study was to quantitatively measure the extent at which speech recognition methods can…

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is…

The typical contrastive self-supervised algorithm uses a similarity measure in latent space as the supervision signal by contrasting positive and negative images directly or indirectly. Although the utility of self-supervised algorithms has…

The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ended instruction following. These domains often rely on LLM…

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative…

Prior efforts in building computer-assisted pronunciation training (CAPT) systems often treat automatic pronunciation assessment (APA) and mispronunciation detection and diagnosis (MDD) as separate fronts: the former aims to provide…

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored…

Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering updates but often…

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called…

User intentions are typically formalized as evaluation rewards to be maximized when fine-tuning language models (LMs). Existing alignment methods, such as Direct Preference Optimization (DPO), are mainly tailored for pairwise preference…

Although automatic pathological speech detection approaches show promising results when clean recordings are available, they are vulnerable to additive noise. Recently it has been shown that databases commonly used to develop and evaluate…

In our previous work, a reduced order model (ROM) for a stochastic system was made, where noisy data was projected onto principal component analysis (PCA)-derived basis vectors to obtain an accurate reconstruction of the noise-free data.…

Recently, phonetic posteriorgrams (PPGs) based methods have been quite popular in non-parallel singing voice conversion systems. However, due to the lack of acoustic information in PPGs, style and naturalness of the converted singing voices…

Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to…

Phoneme boundary detection plays an essential first step for a variety of speech processing applications such as speaker diarization, speech science, keyword spotting, etc. In this work, we propose a neural architecture coupled with a…

The rise of video-sharing platforms has attracted more and more people to shoot videos and upload them to the Internet. These videos mostly contain a carefully-edited background audio track, where serious speech change, pitch shifting and…