Related papers: Lattice-based lightly-supervised acoustic model tr…

In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel…

Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to…

Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…

Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g., speech…

Transmission line state assessment and prediction are of great significance for the rational formulation of operation and maintenance strategy and improvement of operation and maintenance level. Aiming at the problem that existing models…

This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition. We propose a novel loss function $\unicode{x2013}$ SoftCTC $\unicode{x2013}$ which is an extension of…

Continual learning (CL), or domain expansion, recently became a popular topic for automatic speech recognition (ASR) acoustic modeling because practical systems have to be updated frequently in order to work robustly on types of speech not…

We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising…

Target sound detection (TSD) aims to detect the target sound from mixture audio given the reference information. Previous works have shown that TSD models can be trained on fully-annotated (frame-level label) or weakly-annotated (clip-level…

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In…

Knowing the link between observed predictive variables and outcomes is crucial for making inference in any regression model. When this link is missing, partially or completely, classical estimation methods fail in recovering the true…

We present a rapid design methodology that combines automated hyper-parameter tuning with semi-supervised training to build highly accurate and robust models for voice commands classification. Proposed approach allows quick evaluation of…

Semantic correspondence methods have advanced to obtaining high-quality correspondences employing complicated networks, aiming to maximize the model capacity. However, despite the performance improvements, they may remain constrained by the…

Maximum mutual information (MMI) is a model selection criterion used for hidden Markov model (HMM) parameter estimation that was developed more than twenty years ago as a discriminative alternative to the maximum likelihood criterion for…

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

In this paper, we describe recent performance improvements to the production Marchex speech recognition system for our spontaneous customer-to-business telephone conversations. In our previous work, we focused on in-domain language and…

Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Optical character recognition (OCR) can be used to produce digitized text, and previous work has demonstrated the…

This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech. Most existing algorithms rely on paired dry/wet data, which is difficult to obtain, or…

In this paper we present a novel Neural Network algorithm for conducting semi-supervised learning for sequence labeling tasks arranged in a linguistically motivated hierarchy. This relationship is exploited to regularise the representations…

This paper proposes a self-regularised minimum latency training (SR-MLT) method for streaming Transformer-based automatic speech recognition (ASR) systems. In previous works, latency was optimised by truncating the online attention weights…