5 papers
WER we are and WER we think we are
Piotr Szymański, Piotr Żelasko, Mikolaj Morzy +6
Natural language processing of conversational speech requires the availability of high-quality transcripts. In this paper, we express our skepticism towards the recent reports of v…
Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?
Łukasz Augustyniak, Piotr Szymanski, Mikołaj Morzy +5
Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These…
Avaya Conversational Intelligence: A Real-Time System for Spoken Language Understanding in Human-Human Call Center Conversations
Jan Mizgajski, Adrian Szymczak, Robert Głowski +14
Avaya Conversational Intelligence(ACI) is an end-to-end, cloud-based solution for real-time Spoken Language Understanding for call centers. It combines large vocabulary, real-time…
Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition
Piotr Żelasko, Jan Mizgajski, Mikołaj Morzy +4
In this paper, we present a method for correcting automatic speech recognition (ASR) errors using a finite state transducer (FST) intent recognition framework. Intent recognition i…
Punctuation Prediction Model for Conversational Speech
Piotr Żelasko, Piotr Szymański, Jan Mizgajski +3
An ASR system usually does not predict any punctuation or capitalization. Lack of punctuation causes problems in result presentation and confuses both the human reader andoff-the-s…