Related papers: Recognition Performance of a Structured Language M…

In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from…

In recent years, transformer-based language models have achieved state of the art performance in various NLP benchmarks. These models are able to extract mostly distributional information with some semantics from unstructured text, however…

State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncertainty and lead to over-fitting and poor generalization when…

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

We describe the 2017 version of Microsoft's conversational speech recognition system, in which we update our 2016 system with recent developments in neural-network-based acoustic and language modeling to further advance the state of the art…

Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…

Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a…

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are…

Human language understanding operates at multiple levels of granularity (e.g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined. However, existing deep models with stacked layers do…

Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components and support the development of more inclusive speech and language technologies. Inspired by the…

Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…

A statistical model for segmentation and word discovery in child directed speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described and results of empirical tests showing…

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal…

Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, despite its…

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit…

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar…

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they…