Most language understanding models in task-oriented dialog systems are trained on a small
amount of annotated training data, and evaluated in a small set from the same distribution …

End-to-end neural TTS has achieved excellent performance on reading style speech
synthesis. However, it is still a challenge to build a high-quality conversational TTS due to …

Using spontaneous conversational speech for TTS raises questions on how disfluencies
such as filled pauses (FPs) should be approached. Detailed annotation of FPs in training …

Inserting fillers (such as “um”,“like”) to clean speech text has a rich history of study. One
major application is to make dialogue systems sound more spontaneous. The ambiguity of …

Spontaneous speaking style exhibits notable differences from other speaking styles due to
various spontaneous phenomena (eg, filled pauses, prolongation) and substantial prosody …

In this paper, we propose a method to generate personalized filled pauses (FPs) with group-
wise prediction models. Compared with fluent text generation, disfluent text generation has …

Disfluency occurs regularly in natural, everyday speech. Such phenomena as silent pauses,
filled pauses (uh, um in English) and repairs occur with regular frequency and training data …

The study of natural language is present in multiple scientific disciplines. In linguistics, this
study is purpose itself and comes in many specific areas. In neuro-sciences also, language …

Large vocabulary Automatic Speech Recognition (ASR) systems require a huge amount of
human transcribed speech data. Such speech corpora are either purchased from dataset …

Disclosed embodiments relate to aligning pairs of sentences. Techniques can include
receiving a plurality of sentences; generating a graph for each of at least two sentences of …