Noise Suppression
THE STANDARD NOISE SUPPRESSION ALGORITHM IS A LOW-MIPS, LOW-COMPLEXITY ALTERNATIVE TO NOISE REDUCTION
The Adaptive Digital noise suppression software reduces background noise that is present in speech signals during periods between speech periods.
Features List
- Functions are C-callable.
- Multi-channel capable
- Completely re-entrant (Channel can interrupt any Channel, any time)
- Can be integrated with echo cancellers, VOX, and tone detection/regeneration.
- Programmable parameters
Availability
Platforms Texas Instruments – TI TMS320C7000 C7x | TI TMS320C6000 C64x/C64x+/C66x/C674x | TI TMS320C5000 C55x / Legacy C54x
ADT Noise Suppress is available on the above platforms: Other configurations are available upon request.
Specifications
NOTE: We specify MIPS (Millions of Instructions Per Second) as MCPS (Millions of Instruction Cycles Per Second). Unless otherwise specified, peak MIPS are indicated.
↓ Click on links below to view specification tables.
Note: All CPU usage given in MIPS (also known as MCPS or MHz)
Noise Suppress C64x / C64x+ / C66x / C674x || C7x
CPU UTILIZATION & MEMORY REQUIREMENTSAll Memory usage is given in units of byte.
| Software | MIPS (Peak) | Program Memory | Scratch Memory | Per-channel Memory |
| NS | 0.2 | 2400 | 84 | 24 |
Noise Suppress C55x
CPU UTILIZATION & MEMORY REQUIREMENTSAll Memory usage is given in units of byte.
| Software | MIPS (Peak) | Program Memory | Scratch Memory | Tables | Per-channel Memory |
| NS | 0.35 | 1012 | 384 | 4332 | 108 |
Noise Suppress C54x
CPU UTILIZATION & MEMORY REQUIREMENTSAll Memory usage is given in 16-bit word.
| Software | MIPS (Peak) | Program Memory | Scratch Memory | Per-channel Memory |
| NS | 0.3 | 400 | 42 | 12 |
Description
The Adaptive Digital noise suppression software reduces background noise that is present in speech signals during periods between speech periods, but not during the actual speech periods.
| Algorithm Version | CPU Utilization | Memory | Delay | SNR Improvement | Frequency / Time Based |
| Noise Reduction | High | High | Moderate | Yes | Frequency |
| Noise Suppression | Low | Low | None | No | Time |
The user can configure either version’s cancellation settings to be more or less aggressive. Less aggressive settings reduce noise by a moderate amount while more aggressive settings reduce noise by a greater degree.
One might wonder why a system would be configured with a less aggressive setting. There are a few reasons. One reason is that a very aggressive setting can result in loss of desired signal. Another reason is that, in the case of the low complexity version, an aggressive setting will cause an accentuated difference between the noise level during speech and the noise level when speech is not present. The transitions between speech and no speech may become more objectionable with the more aggressive setting.
Function API's
API function call summary
NS_ADT_init( . . .) Initiates a channel of Noise Suppression
NS_ADT_reduce( . . . ) Executes Noise Suppression