Length- and Noise-aware Training Techniques for Short-utterance Speaker Recognition
Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker recognition systems. The x-vector framework is a popular choice for generating speaker embeddings in recent literature due to its robust training mechanism and excellent performance in various test sets. In this paper, we start with early work on including invariant representation learning (IRL) to the loss function and modify the approach with centroid alignment (CA) and length variability cost (LVC) techniques to further improve robustness in noisy, far-field applications. This work mainly focuses on improvements for short-duration test utterances (1-8s). We also present improved results on long-duration tasks. In addition, this work discusses a novel self-attention mechanism. On the VOiCES far-field corpus, the combination of the proposed techniques achieves relative improvements of 7.0% for extremely short and 8.2% for full-duration test utterances on equal error rate (EER) over our baseline system.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSpeaker RecognitionSimilar Papers 제목 키워드 기반
Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings
Neural Machine Translation often suffers from an under-translation problem due to its limited modeling of output sequence lengths. In this work, we propose a novel approach to training a Transformer model using length co…
Machine TranslationPredictionSentenceTranslationLength-Aware DETR for Robust Moment Retrieval
Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query. Given the prevalent use of platforms like YouTube for information retrieval, the demand for MR techniques is si…
Information RetrievalMoment RetrievalRetrievalVH-Diffuser: Variable Horizon Diffusion Planner for Time-Aware Goal-Conditioned Trajectory Planning
Diffusion-based planners have gained significant recent attention for their robustness and performance in long-horizon tasks. However, most existing planners rely on a fixed, pre-specified horizon during both training an…
Trajectory PlanningRobust Stochastic Shortest-Path Planning via Risk-Sensitive Incremental Sampling
With the pervasiveness of Stochastic Shortest-Path (SSP) problems in high-risk industries, such as last-mile autonomous delivery and supply chain management, robust planning algorithms are crucial for ensuring successful…
ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs
Scaling long-context ability is essential for Large Language Models (LLMs). To amortize the memory consumption across multiple devices in long-context training, inter-data partitioning (a.k.a. Data Parallelism) and intra…