--- schema: 1 type: video title: >- Contact Center Voice AI: Low-Latency Intelligence Extraction from Messy Audio Streams — Dippu Singh description: >- "Processing real-time voice data is an engineering minefield of latency, accents, and interruptions. This session explores the architecture of a Real-Time Voice Intelligence Pipeline deployed in a high-volume contact center. We will move beyond simple transcription to discuss Structured Intent Extraction. I will show you how to design: 1. Voice Capture Pipeline: The entry point for clean, multi-channel data acquisition. 2. Speech-To-Text(STT) Engine: Converting speech to accurate text. 3. Generative AI Core Structure: Using rigorous system prompts to force the LLM to separate ""Customer Intent"" from ""Operator Chit-Chat"" and output valid JSON, even from garbled transcripts. 4. Customer Data Sync: Translating AI insights into enterprise system actions. We reduced post-call work by 50% by shifting compute from ""batch"" to ""stream."" Speaker: Dippu Kumar Singh - Leader Of Emerging Technologies (Apps), Fujitsu North America Inc. Dippu Kumar Singh has over 16 years of experience at the intersection of industry innovation and advanced research. He is a recognized authority in building scalable, trustworthy, and commercially viable AI systems. Being a Leader for Emerging Data & Analytics at Fujitsu North America, Dippu specializes in bridging the gap between theoretical AI concepts and enterprise-grade implementation. His strategic leadership has spearheaded multi-million in sales pipelines and delivered remarkable savings through AI-driven optimizations in transportation, manufacturing, utilities, and supply chain logistics. Socials: https://www.linkedin.com/in/dippukumarsingh/ Slides: https://docs.google.com/presentation/d/1f2y1s64irhdDNTRgK6bWrBtOgMWlhQYM/edit?usp=sharing&ouid=107532212133041789455&rtpof=true&sd=true" canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/contact-center-voice-ai-low-latency-intelligence-ex-af1940e66f39 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/contact-center-voice-ai-low-latency-intelligence-ex-af1940e66f39.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T15:31:40.118Z' language: null children: [] videoId: IEF842ZEU5A durationSeconds: 1376 publishedAt: '2026-04-08T11:45:02.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 261 endSeconds: 346 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=261' heldReason: rights - ordinal: 1 text: null startSeconds: 440 endSeconds: 451 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=440' heldReason: rights - ordinal: 2 text: null startSeconds: 451 endSeconds: 563 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=451' heldReason: rights - ordinal: 3 text: null startSeconds: 563 endSeconds: 574 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=563' heldReason: rights - ordinal: 4 text: null startSeconds: 574 endSeconds: 656 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=574' heldReason: rights - ordinal: 5 text: null startSeconds: 656 endSeconds: 668 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=656' heldReason: rights - ordinal: 6 text: null startSeconds: 668 endSeconds: 765 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=668' heldReason: rights - ordinal: 7 text: null startSeconds: 765 endSeconds: 778 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=765' heldReason: rights - ordinal: 8 text: null startSeconds: 778 endSeconds: 868 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=778' heldReason: rights - ordinal: 9 text: null startSeconds: 879 endSeconds: 968 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=879' heldReason: rights - ordinal: 10 text: null startSeconds: 980 endSeconds: 1082 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=980' heldReason: rights - ordinal: 11 text: null startSeconds: 1082 endSeconds: 1094 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=1082' heldReason: rights - ordinal: 12 text: null startSeconds: 1094 endSeconds: 1174 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=1094' heldReason: rights - ordinal: 13 text: null startSeconds: 1184 endSeconds: 1319 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=1184' heldReason: rights - ordinal: 14 text: null startSeconds: 1184 endSeconds: 1319 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=1184' heldReason: rights - ordinal: 15 text: null startSeconds: 1184 endSeconds: 1319 watch: 'https://liquidgold.cc/watch/IEF842ZEU5A?t=1184' heldReason: rights --- # Contact Center Voice AI: Low-Latency Intelligence Extraction from Messy Audio Streams — Dippu Singh "Processing real-time voice data is an engineering minefield of latency, accents, and interruptions. This session explores the architecture of a Real-Time Voice Intelligence Pipeline deployed in a high-volume contact center. We will move beyond simple transcription to discuss Structured Intent Extraction. I will show you how to design: 1. Voice Capture Pipeline: The entry point for clean, multi-channel data acquisition. 2. Speech-To-Text(STT) Engine: Converting speech to accurate text. 3. Generative AI Core Structure: Using rigorous system prompts to force the LLM to separate ""Customer Intent"" from ""Operator Chit-Chat"" and output valid JSON, even from garbled transcripts. 4. Customer Data Sync: Translating AI insights into enterprise system actions. We reduced post-call work by 50% by shifting compute from ""batch"" to ""stream."" Speaker: Dippu Kumar Singh - Leader Of Emerging Technologies (Apps), Fujitsu North America Inc. Dippu Kumar Singh has over 16 years of experience at the intersection of industry innovation and advanced research. He is a recognized authority in building scalable, trustworthy, and commercially viable AI systems. Being a Leader for Emerging Data & Analytics at Fujitsu North America, Dippu specializes in bridging the gap between theoretical AI concepts and enterprise-grade implementation. His strategic leadership has spearheaded multi-million in sales pipelines and delivered remarkable savings through AI-driven optimizations in transportation, manufacturing, utilities, and supply chain logistics. Socials: https://www.linkedin.com/in/dippukumarsingh/ Slides: https://docs.google.com/presentation/d/1f2y1s64irhdDNTRgK6bWrBtOgMWlhQYM/edit?usp=sharing\&ouid=107532212133041789455\&rtpof=true\&sd=true" Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/contact-center-voice-ai-low-latency-intelligence-ex-af1940e66f39 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks --- #### Chunk 0: Document excerpt (0:00 to 1:56) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 1: Document excerpt (1:56 to 2:06) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 2: Document excerpt (2:06 to 4:10) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 3: Document excerpt (4:10 to 5:46) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 4: Document excerpt (5:46 to 5:57) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 5: Document excerpt (5:57 to 7:31) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 6: Document excerpt (7:31 to 9:34) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 7: Document excerpt (9:34 to 11:08) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 8: Document excerpt (11:08 to 12:58) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 9: Document excerpt (12:58 to 14:39) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 10: Document excerpt (14:39 to 16:20) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 11: Document excerpt (16:20 to 18:14) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 12: Document excerpt (18:14 to 19:34) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 13: Document excerpt (19:34 to 19:44) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 14: Document excerpt (19:44 to 21:59) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 15: Document excerpt (21:59 to 22:56) > Held: transcript rights do not permit this chunk's text.