Related papers: Device-Directed Speech Detection: Regularization v…

This paper presents a cost-effective, low-power approach to unintentional fall detection using knowledge distillation-based LSTM (Long Short-Term Memory) models to significantly improve accuracy. With a primary focus on analyzing…

We propose a novel approach for semi-supervised learning (SSL) designed to overcome distribution shifts between training and real-world data arising in the keyword spotting (KWS) task. Shifts from training data distribution are a key…

Voice activity detection is an essential pre-processing component for speech-related tasks such as automatic speech recognition (ASR). Traditional supervised VAD systems obtain frame-level labels from an ASR pipeline by using, e.g., a…

Recent Vision-based Large Language Models~(VisionLLMs) for autonomous driving have seen rapid advancements. However, such promotion is extremely dependent on large-scale high-quality annotated data, which is costly and labor-intensive. To…

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting starting only from unlabeled seed questions with no ground-truth…

The ongoing biodiversity crisis, driven by factors such as land-use change and global warming, emphasizes the need for effective ecological monitoring methods. Acoustic monitoring of biodiversity has emerged as an important monitoring tool.…

Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to…

Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform…

Deploying language models (LMs) in customer-facing speech applications requires conversational fluency and adherence to specific stylistic guidelines. This can be challenging to achieve reliably using complex system prompts due to issues…

Mispronunciation Detection and Diagnosis (MDD) is crucial for language learning and speech therapy. Unlike conventional methods that require scoring models or training phoneme-level models, we propose a novel training-free framework that…

It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models…

As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training…

Training robust speaker verification systems without speaker labels has long been a challenging task. Previous studies observed a large performance gap between self-supervised and fully supervised methods. In this paper, we apply a…

The goal of this work is to train strong models for visual speech recognition without requiring human annotated ground truth data. We achieve this by distilling from an Automatic Speech Recognition (ASR) model that has been trained on a…

We study device-addressed speech detection under pre-ASR edge deployment constraints, where systems must decide whether to forward audio before transcription under strict latency and compute limits. We show that, in multi-speaker…

Topic modeling is a dominant method for exploring document collections on the web and in digital libraries. Recent approaches to topic modeling use pretrained contextualized language models and variational autoencoders. However, large…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled data is limited but one has access to a large pool of unlabeled…