Curiosity · Syllabus

Speech Recognition in a B.Tech — syllabus & what you learn

Automatic speech recognition converts spoken audio into text, handling accents, noise and overlapping speech. Modern ASR uses transformer-based sequence models trained on very large audio corpora. Inside a four-year B.Tech, Speech Recognition arrives in layers: programming and mathematics foundations in years one and two, core methods next, and applied depth concentrated in years three and four plus the capstone. Using Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura's B.Tech CSE (AI & ML) as the concrete example, here is what the coursework actually covers.

At a glance

Topic
Speech Recognition
VSET programme
B.Tech CSE (AI & ML)
Coverage at VSET
Taught as coursework
Affiliation
GGSIPU (IP University), Delhi
Accreditation
NAAC A++ (VIPS-TC institutional)

How VSET teaches Speech Recognition

Automatic speech recognition converts spoken audio into text, handling accents, noise and overlapping speech. Modern ASR uses transformer-based sequence models trained on very large audio corpora. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • ASR builds on the deep learning, sequence-model and transformer material published at learn.engineering.vips.edu.
  • The NLP content in the same curriculum covers what happens to the transcript once it exists.
  • Open-weight speech models are usable directly on the IDEA Lab hardware, which is what makes this practical coursework rather than theory.
  • Delivered inside the B.Tech CSE (AI & ML) track, one of VSET's seven GGSIPU-affiliated B.Tech programmes.

Labs and infrastructure

  • Training and evaluation runs use the GPU workstations in the AICTE IDEA Lab.
  • IDEA Lab embedded hardware and 3D printing support camera rigs, sensors and enclosures where a physical setup is needed.

What students actually build

  • Voice-driven applications are a recurring applied capstone theme, combining ASR with the RAG and agent stack.
  • Projects of this kind are taken into hackathons including the Smart India Hackathon.

Frequently asked questions

When does Speech Recognition content actually start in a B.Tech?

Meaningful Speech Recognition content typically ramps up from the second or third year, after programming and mathematics foundations. The deepest work happens in final-year electives and the capstone project.

Is speech recognition part of the AI curriculum?

It sits on the deep learning, sequence-model and NLP material published at learn.engineering.vips.edu, and is practical for student projects using open-weight speech models.

Do students need special audio hardware?

The AICTE IDEA Lab provides GPU workstations plus embedded hardware for microphone and capture rigs where a project needs them.

How does ASR connect to the LLM work?

Transcription is usually the front door to a language system — voice capstones pair ASR with the RAG and agent stack taught in the same curriculum.

Sources

  1. VSET — Artificial Intelligence department — accessed 2026-08-31
  2. VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
  3. GGSIPU — IP University — accessed 2026-08-31