Effect of Pronunciations on OOV Queries in Spoken Term Detection D. - PowerPoint PPT Presentation

Effect of Pronunciations on OOV Queries in Spoken Term Detection D. Can 1 E. Cooper 2 A. Sethy 3 C. White 4 B. Ramabhadran 3 M. SaraÃ § lar 1 1 2 3 4

Introduction Methods Experiments Summary Outline Introduction 1 Spoken Term Detection Task Motivation Methods 2 WFST-based Spoken Term Detection Query Forming and Expansion for Phonetic Search Experiments 3 Experimental Setup Results Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Outline Introduction 1 Spoken Term Detection Task Motivation Methods 2 WFST-based Spoken Term Detection Query Forming and Expansion for Phonetic Search Experiments 3 Experimental Setup Results Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Anatomy of a Spoken Term Detection (STD) System Speech User Retrieve Database yes larger Query ASR no than τ ? Dispose Search Preprocess Index Engine Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Anatomy of a Spoken Term Detection (STD) System Speech User Retrieve Database yes larger Query ASR no than τ ? Dispose INDEXING Search Preprocess Index Engine Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Anatomy of a Spoken Term Detection (STD) System Speech User Retrieve Database yes SEARCH larger Query no than τ ? Dispose Search Preprocess Index Engine Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Anatomy of a Spoken Term Detection (STD) System Speech User Retrieve Database yes RETRIEVAL larger Query no than τ ? Dispose Search Preprocess Index Engine Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Outline Introduction 1 Spoken Term Detection Task Motivation Methods 2 WFST-based Spoken Term Detection Query Forming and Expansion for Phonetic Search Experiments 3 Experimental Setup Results Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Challenges of the Spoken Term Detection Task Aim: Open vocabulary search Reference: “Taipei night view" Challenge: Unreliable transcriptions ASR Output: “tie bay light view" High error rate of one-best transcripts 1 Alternative transcriptions: [tie bay [light 0.6, night 0.4] view] Out-Of-Vocabulary queries 2 Phonetic search: /t ay b ey n ay t v iy w/ Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods Spoken Term Detection Task Experiments Motivation Summary Challenges of the Spoken Term Detection Task Aim: Open vocabulary search Reference: “Taipei night view" Challenge: Unreliable transcriptions ASR Output: “tie bay light view" High error rate of one-best transcripts 1 Efficient Indexing and Search of Alternatives Out-Of-Vocabulary queries 2 OOV Pronunciation Modeling Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods WFST-based Spoken Term Detection Experiments Query Forming and Expansion for Phonetic Search Summary Outline Introduction 1 Spoken Term Detection Task Motivation Methods 2 WFST-based Spoken Term Detection Query Forming and Expansion for Phonetic Search Experiments 3 Experimental Setup Results Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods WFST-based Spoken Term Detection Experiments Query Forming and Expansion for Phonetic Search Summary Index for Spoken Utterance Retrieval [Allauzen et al., 2004] Database: Index: “a a" 1 a: ǫ /1 1 3 a/1 a/1 ǫ :2/.4 ǫ :1/2 0 1 2 a: ǫ /1 ǫ :1/1 ǫ :2/1.4 “[b .6, a .4] a" 2 b/.6 a/1 0 5 0 1 2 ǫ :2/.6 a/.4 b: ǫ /1 ǫ :2.6 a/1 Query: 0 1 2 4 a: ǫ /1 Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods WFST-based Spoken Term Detection Experiments Query Forming and Expansion for Phonetic Search Summary Index for Spoken Utterance Retrieval [Allauzen et al., 2004] Database: Results: “a a" 1 ǫ :1/2 a/1 a/1 0 1 2 a: ǫ /1 0 1 2 ǫ :2/1.4 (Utterance ID, Expected Count): “[b .6, a .4] a" 2 (1,2) b/.6 a/1 1 (2,1.4) 2 0 1 2 a/.4 a/1 Query: 0 1 Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Introduction Methods WFST-based Spoken Term Detection Experiments Query Forming and Expansion for Phonetic Search Summary 2-pass Retrieval for STD [Parlak and Saraclar, 2008] Procedure For each query: Obtain (utterance ID, expected count) pairs (1 st pass) For each utterance with expected count > τ : Align the query with the utterance → time interval (2 nd pass) Return (utterance ID, time interval, expected count) triplet Problems 2 nd pass takes time → slow Multiple occurrences of a query in the same utterance contribute to the same expected count. Ideal for Spoken Utterance Retrieval Not so for Spoken Term Detection Can, Cooper, Sethy, White, Ramabhadran, SaraÃ § lar Effect of Pronunciations on OOV Queries in STD

Effect of Pronunciations on OOV Queries in Spoken Term Detection D. - PowerPoint PPT Presentation

Effect of Pronunciations on OOV Queries in Spoken Term Detection D. Can 1 E. Cooper 2 A. Sethy 3 C. White 4 B. Ramabhadran 3 M. Sara lar 1 1 2 3 4 Introduction Methods Experiments Summary Outline Introduction 1 Spoken Term

Web-derived Pronunciations for Spoken Term Detection Doan Can Boazii University Erica

Web-derived Pronunciations Arnab Ghoshal Spoken Langauge Systems, Saarland University Research

Score Distribution Based Term Specific Thresholding for Spoken Term Detection D. Can M. Sarac

Joint Learning of Phonetic Units and Word Pronunciations for ASR Chia-ying (Jackie) Lee, Yu

Queries in PSM The following rules apply to the use of queries: CS 235: 1. Queries

EECS E6870: Lecture 12: Special Topics Spoken Term Detection Stanley F. Chen, Michael A.

Spoken Language Structure Hsin-min Wang References: - X. Huang et al., Spoken Language

Grounding LING 575: Spoken Dialog Systems May 12 th , 2016 1 What is Grounding? Spoken Dialog

Transaction Management Manage many queries/updates running simultaneously. CS 235:

THE SPOKEN BLESSING Numbers 6:22 27 Since the start of human history, the spoken blessing

Spoken Language Structure Berlin Chen 2003 References: - X. Huang et. al., Spoken Language

STANDARDS IN SPOKEN CORPORA OUTLINE (1) Case study: Spoken

Women in Mining: Long-term trends and the effect of the economic cycle Bronwyn Bell August 2018

Spoken and Sign Languages Spoken and Sign Languages A Cross Modal Study Purushottam Kar Achla

Spoken Language Structure Berlin Chen 2004 References: - X. Huang et. al., Spoken Language

Module 14: Analyzing Queries Overview Queries That Use the AND Operator the OR

New Requirements Top-N/Bottom-N queries Interactive queries Decision making

Uncertainty in Spoken Uncertainty in Spoken Multimodal - speakers have intentions - speech,

Diversity Day on the 4 th June! How many languages do you think are spoken at CHSG by the

Long-term effect of displacement in Japan in Japan Mayu FUJII, NIPSSR Ryo KAMBAYASHI, IER,

Speech Processing 11-492/18-492 Spoken Term Detection/Key Word Spotting Listening for Keywords

What Is Generative? A Long-term Effect of Signs of Safety Practice Ai Ai Hi Hish shikawa

TRUE-AHF Trial Short- and Long-Term Effect of Immediate Vasodilator Therapy in Acutely

Effect of Empirical Left Atrial Appendage Isolation on long-term procedure outcome in patients