Related papers: CB-Conformer: Contextual biasing Conformer for bia…
Recent research on word-level confidence estimation for speech recognition systems has primarily focused on lightweight models known as Confidence Estimation Modules (CEMs), which rely on hand-engineered features derived from Automatic…
In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The…
Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…
This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…
Neural contextual biasing effectively improves automatic speech recognition (ASR) for crucial phrases within a speaker's context, particularly those that are infrequent in the training data. This work proposes contextual text injection…
We present a system for the Zero Resource Speech Challenge 2021, which combines a Contrastive Predictive Coding (CPC) with deep cluster. In deep cluster, we first prepare pseudo-labels obtained by clustering the outputs of a CPC network…
End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse…
Concept Bottleneck Models (CBMs) provide inherent interpretability by first predicting a set of human-understandable concepts and then mapping them to labels through a simple classifier. While users can intervene in the concept space to…
Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during…
With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods…
The ability to perform offline A/B-testing and off-policy learning using logged contextual bandit feedback is highly desirable in a broad range of applications, including recommender systems, search engines, ad placement, and personalized…
Low-Rank Adaptation (LoRA) offers a cost-effective solution for fine-tuning large language models (LLMs), but it often produces overconfident predictions in data-scarce few-shot settings. To address this issue, several classical statistical…
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…
Recent models for unsupervised representation learning of text have employed a number of techniques to improve contextual word representations but have put little focus on discourse-level representations. We propose CONPONO, an…
The recently proposed Conformer model has become the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture that captures both local and global features. However, through a series…
Conversational speech synthesis (CSS) incorporates historical dialogue as supplementary information with the aim of generating speech that has dialogue-appropriate prosody. While previous methods have already delved into enhancing context…
Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…
Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such…
Goal-oriented conversational interfaces are designed to accomplish specific tasks and typically have interactions that tend to span multiple turns adhering to a pre-defined structure and a goal. However, conventional neural language models…
The increasingly large size of modern pretrained language models not only makes them inherit more human-like biases from the training corpora, but also makes it computationally expensive to mitigate such biases. In this paper, we…