8 papers
Cross-stitched Multi-modal Encoders
Karan Singla, Daniel Pressel, Ryan Price +3
In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jo…
Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
Karan Singla, Shahab Jalalvand, Yeon-Jun Kim +3
Person name capture from human speech is a difficult task in human-machine conversations. In this paper, we propose a novel approach to capture the person names from the caller utt…
Unsupervised Spoken Utterance Classification
Shahab Jalalvand, Srinivas Bangalore
An intelligent virtual assistant (IVA) enables effortless conversations in call routing through spoken utterance classification (SUC) which is a special form of spoken language und…
Intent Features for Rich Natural Language Understanding
Brian Lester, Sagnik Ray Choudhury, Rashmi Prasad +1
Complex natural language understanding modules in dialog systems have a richer understanding of user utterances, and thus are critical in providing a better user experience. Howeve…
Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers
Brian Lester, Daniel Pressel, Amy Hemmeter +2
Current state-of-the-art models for named entity recognition (NER) are neural models with a conditional random field (CRF) as the final layer. Entities are represented as per-token…
Multiple Word Embeddings for Increased Diversity of Representation
Brian Lester, Daniel Pressel, Amy Hemmeter +2
Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of…